Sparse Autoencoders

Also known as SAE

Follow this topic Ask about this topic

Momentum

16 papers in the last four weeks, up 100% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 149

May 6, 2026cs.LG

Feature Starvation as Geometric Instability in Sparse Autoencoders

Sparse autoencoders (SAEs) are used to disentangle the dense, polysemantic internal representations of large language models (LLMs) into interpretable, monosemantic concepts. However, standard

\ell_1

-regularized SAEs suffer from feature starvation (dead neurons) and shrinkage bias, often requiring computationally expensive heuristic resampling and nondifferentiable hard-masking methods to bypass these challenges. We argue that feature starvation is not merely an empirical artifact of poor data diversity, but a fundamental optimization-geometric pathology of overcomplete dictionaries: the

\ell_1

-induced sparse coding map is unstable and fundamentally misaligned with shallow, amortized encoders. To address this structural instability, we introduce adaptive elastic net SAEs (AEN-SAEs), a fully differentiable architecture grounded in classical sparse regression. AEN-SAEs combine an

\ell_2

structural term that enforces strong convexity and Lipschitz stability with adaptive

\ell_1

reweighting that eliminates shrinkage bias and suppresses spurious features, thereby jointly controlling the curvature and interaction structure of the induced polyhedral geometry. Theoretically, we show that AEN-SAEs yield a Lipschitz-continuous sparse coding map and recover the global feature support under mild assumptions. Empirically, across synthetic settings and LLMs (Pythia 70M, Llama 3.1 8B), AEN-SAEs mitigate feature starvation without auxiliary heuristics while maintaining competitive reconstruction abilities.

Faris Chaudhry, Keisuke Yano, Anthea Monod

Imperial College London South Kensington Campus, London SW7 2AZ, UK · Institute for Statistical Mathematics 10-3 Midori-cho, Tachikawa Tokyo 190-8562, Japan

Representation Learning Sparse Autoencoders Mechanistic Interpretability Sparse Coding

May 4, 2026cs.LG

Pairwise matrices for sparse autoencoders: single-feature inspection mislabels causal axes

The standard sparse-autoencoder (SAE) interpretability protocol labels each feature from its top-activating contexts and validates by single-feature steering. We propose the pairwise matrix protocol, co-varying steering coefficient with joint condition, and report three findings the standard one-corner protocol misses on Qwen3-1.7B-Instruct, replicated on Gemma-2-2B-it. First, a feature labelled "AI self-disclaimer" from its top contexts produces an inverted U-shape under a coefficient sweep: at c=+500 the model substitutes a fluent contemplative-philosopher voice for the disclaimer. Two further features anchor the criterion (one monotonic, one pure breakdown). Second, three near-orthogonal cluster-specific features that individually steer a philosophy-of-mind register, jointly suppressed at c=-500, damage grounded composition on recipes and engine explanations as well as introspective prompts; single-feature suppression at the same magnitude leaves controls intact. Third, a matched-geometry comparison of single-feature, joint, and random-direction perturbations (norm ~1.55, cosine ~0.64) yields three distinct output regimes: single-feature substitutes strategy filler, random direction substitutes diverse content, joint suppression alone produces placeholder text. Coherence loss is direction-pattern-dependent, not magnitude-dependent. All three findings reproduce on Gemma with model-specific damage signatures; the matched-geometry control is CI-separated by ~10x. The pipeline also locates a top causally responsible feature in Llama-3.1-8B-Instruct.

Michael A. Riegler, Birk Sebastian Frostelid Torpmann-Hagen

SimulaMet, Norway · Simula, Norway

Sparse Autoencoders Mechanistic Interpretability Causal Interventions in Language Models Activation Steering

May 3, 2026cs.LG

Feature Rivalry in Sparse Autoencoder Representations: A Mechanistic Study of Uncertainty-Driven Feature Competition in LLMs

Sparse Autoencoders (SAEs) decompose large language model representations into interpretable features, but how these features interact under uncertainty remains poorly understood. We introduce Feature Rivalry -- negatively correlated SAE feature pairs -- and study whether rivalry serves as a mechanistic signature of model uncertainty in Gemma-2-2B using Gemma Scope SAEs. Through a controlled within-domain experiment on PopQA split by response entropy, we find that high-entropy questions produce significantly stronger feature rivalry at layers 0 and 12 relative to low-entropy questions (p=5.3x10^-26 and p=5.8x10^-5 respectively), localizing uncertainty to specific processing stages in the residual stream. We then test whether rivalry is causally upstream of model outputs via activation steering along rivalry axes -- finding that steering along the rivalry direction (vec_A - vec_B) causes more output changes than random directions at low steering multipliers across 15 of 20 rival feature pairs. Finally, a per-prompt rivalry score derived from pairwise cosine similarities of active SAE feature decoder vectors predicts answer correctness (AUROC=0.689), approaching but not matching softmax confidence (AUROC=0.808).

Harshavardhan

Independent Researcher

LLM Interpretability Sparse Autoencoders LLM Uncertainty Estimation

May 3, 2026cs.CV

GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models

Brain MRI foundation models learn rich representations of anatomy, but interpreting what clinical information they encode remains an open problem. Standard sparse autoencoders (SAEs) suffer from severe feature collapse in deep transformer layers, and in Alzheimer's disease (AD) research, aging confounds nearly every clinical variable, making naive annotation unreliable. We propose GeoSAE, a geometry-guided SAE framework that uses the foundation model's learned manifold structure to prevent feature collapse and annotates each surviving feature via age-deconfounded partial correlations. Applied to ~14k T1-weighted MRI scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the Australian Imaging biomarkers and Lifestyle (AIBL) datasets, GeoSAE identifies a compact, fully interpretable feature set that predicts mild cognitive impairment (MCI)-to-AD conversion (AUC 0.746) using only 2% of the embedding dimensions, while comorbidity-annotated features achieve only chance-level performance. The identified features replicate across cohorts without retraining (r=0.97) and localize to neuroanatomically distinct regions consistent with Braak staging. This shows that geometry-guided SAEs can extract interpretable, biomarkers from frozen brain MRI foundation models.

Favour Nerrise, Lucy Yin, Mohammad H. Abbasi +2

Stanford University · Stanford University, CA

Alzheimer's Disease Medical Imaging Foundation Models Clinical Outcome Prediction Geometric Representation Learning Sparse Autoencoders Alzheimer's Disease Classification+3

Apr 30, 2026cs.LG

Do Sparse Autoencoders Capture Concept Manifolds?

Sparse autoencoders (SAEs) are widely used to extract interpretable features from neural network representations, often under the implicit assumption that concepts correspond to independent linear directions. However, a growing body of evidence suggests that many concepts are instead organized along low-dimensional manifolds encoding continuous geometric relationships. This raises three basic questions: what does it mean for an SAE to capture a manifold, when do existing SAE architectures do so, and how? We develop a theoretical framework that answers these questions and show that SAEs can capture manifolds in two fundamentally different ways: globally, by allocating a compact group of atoms whose linear span contains the entire manifold, or locally, by distributing it across features that each selectively tile a restricted region of the underlying geometry. Empirically, we find that SAEs suboptimally recover continuous structures, mixing the global subspace and local tiling solutions in a fragmented regime we call dilution. This explains why manifold structure is rarely visible at the level of individual concepts and motivates post-hoc unsupervised discovery methods that search for coherent groups of atoms rather than isolated directions. More broadly, our results suggest that future representation learning methods should treat geometric objects, not just individual directions, as the basic units of interpretability.

Usha Bhalla, Thomas Fel, Can Rager +9

aHarvard University · bNortheastern University · cTechnion IIT +1

Neural Representation Geometry Sparse Autoencoders Neural Network Interpretability Manifold Learning Sparse Coding

Apr 29, 2026cs.CL

MoRFI: Monotonic Sparse Autoencoder Feature Identification

Large language models (LLMs) acquire most of their factual knowledge during the pre-training stage, through next token prediction. Subsequent stages of post-training often introduce new facts outwith the parametric knowledge, giving rise to hallucinations. While it has been demonstrated that supervised fine-tuning (SFT) on new knowledge may exacerbate the problem, the underlying mechanisms are still poorly understood. We conduct a controlled fine-tuning experiment, focusing on closed-book QA, and find latent directions that causally contribute to hallucinations. Specifically, we fine-tune Llama 3.1 8B, Gemma 2 9B and Mistral 7B v03 on seven distinct single QA datasets, controlling for the percentage of new knowledge and number of training epochs. By measuring performance on the test set, we validate that incrementally introducing new knowledge increases hallucinations, with the effect being more pronounced with prolonged training. We leverage pre-trained sparse autoencoders (SAEs) to analyze residual stream activations across various checkpoints for each model and propose Monotonic Relationship Feature Identification (MoRFI) for capturing causally relevant latents. MoRFI filters SAE features that respond monotonically to controlled fine-tuning data mixtures of a target property. Our findings show that exposure to unknown facts disrupts the model's ability to retrieve stored knowledge along a set of directions in the residual stream. Our pipeline reliably discovers them across distinct models, recovering knowledge through single-latent interventions.

Dimitris Dimakopoulos, Shay B. Cohen, Ioannis Konstas

University of Edinburgh, UK · Heriot-Watt University, UK

LLM Hallucination Mitigation LLM Interpretability LLM Fine-Tuning Hallucination in Language Models Sparse Autoencoders LLM Reliability+2

Apr 29, 2026cs.CV

Sparsity as a Key: Unlocking New Insights from Latent Structures for Out-of-Distribution Detection

Sparse Autoencoders (SAEs) have demonstrated significant success in interpreting Large Language Models (LLMs) by decomposing dense representations into sparse, semantic components. However, their potential for analyzing Vision Transformers (ViTs) remains largely under-explored. In this work, we present the first application of SAEs to the ViT [CLS] token for out-of-distribution (OOD) detection, addressing the limitation of existing methods that rely on entangled feature representations. We propose a novel framework utilizing a Top-k SAE to disentangle the dense [CLS] features into a structured latent space. Through this analysis, we reveal that in-distribution (ID) data exhibits consistent, class-specific activation patterns, which we formalize as Class Activation Profiles (CAPs). Our study uncovers a key structural invariant: while ID samples preserve a stable pattern within CAPs, OOD samples systematically disrupt this structure. Leveraging this insight, we introduce a scoring function based on the divergence of core energy profiles to quantify the deviation from ideal activation profiles. Our method achieves strong results on the FPR95 metric, critical for safety-sensitive applications across multiple benchmarks, while also achieving competitive AUROC. Overall, our findings demonstrate that the sparse, disentangled features revealed by SAEs can serve as a powerful, interpretable tool for robust OOD detection in vision models.

Ahyoung Oh, Wonseok Shin, Songkuk Kim

School of Integrated Technology, BK21 Graduate Program in Intelligent Semiconductor Technology Yonsei University

Sparse Autoencoders OOD Detection

Apr 27, 2026cs.LG

A Unifying Framework for Unsupervised Concept Extraction

Techniques for concept extraction, such as sparse autoencoders and transcoders, aim to extract high-level symbolic concepts from low-level nonsymbolic representations. When these extracted concepts are used for downstream tasks such as model steering and unlearning, it is essential to understand their guarantees, or lack thereof. In this work, we present a unified theoretical framework for unsupervised concept extraction, in which we frame the task of concept extraction as identifying a generative model. We present a general meta-theorem for identifiability, which reduces the problem of establishing identifiability guarantees to the problem of characterizing the intersection of two sets. As we demonstrate on a range of widely-used approaches, this meta-theorem substantially simplifies the task of proving such guarantees, thus paving the way for the development of new, principled approaches for concept extraction.

Chandler Squires, Pradeep Ravikumar

Machine Learning Department, CMU

Unsupervised Learning Parameter Identifiability Sparse Autoencoders

Apr 26, 2026cs.AI

Domain-Filtered Knowledge Graphs from Sparse Autoencoder Features

Sparse autoencoders (SAEs) extract millions of interpretable features from a language model, but flat feature inventories aren't very useful on their own. Domain concepts get mixed with generic and weakly grounded features, while related ideas are scattered across many units, and there's no way to understand relationships between features. We address this by first constructing a strict domain-specific concept universe from a large SAE inventory using contrastive activations and a multi-stage filtering process. Next, we build two aligned graph views on the filtered set: a co-occurrence graph for corpus-level conceptual structure, organized at multiple levels of granularity, and a transcoder-based mechanism graph that links source-layer and target-layer features through sparse latent pathways. Automated edge labeling then turns these graph views into readable knowledge graphs rather than unlabeled layouts. In a case study on a biology textbook, these graphs recover coherent chapter and subchapter-level structure, reveal concepts that bridge neighboring topics, and transform messy sentence-level activity containing thousands of features into compact, readable views that illustrate the model's local activity. Taken together, this reframes a flat SAE inventory as an internal knowledge graph that converts feature-level interpretability into a global map of model knowledge and enables audits of reasoning faithfulness.

John Winnicki, Abeynaya Gnanasekaran, Eric Darve

Institute for Computational and Mathematical Engineering, Stanford University, Stanford, CA, USA

KG Construction LLM Interpretability Sparse Autoencoders Mechanistic Interpretability Knowledge Representation Knowledge Graphs

Apr 25, 2026cs.CL

From Concept-Aligned Tokens to Vulnerable Features: Mechanistic Localization of Jailbreaks

Jailbreak attacks expose a persistent failure mode in safety-aligned LLMs: models can be pushed into harmful behavior, but the internal representations enabling this shift remain poorly localized. Recent mechanistic safety studies often explain such behavior through broad representational objects, including global refusal directions, activation steering vectors, and refusal-related SAE features. We instead ask whether jailbreak vulnerability can be traced to finer-grained, prompt-conditioned SAE feature subgroups. We introduce a token-driven mechanistic pipeline that decomposes the residual stream of Gemma-2-2B into Sparse Autoencoder (SAE) features and identifies feature subgroups associated with unsafe behavior. Using single-category unsafe examples from BeaverTails to reduce cross-category interference, we extract harmful concepts from adversarial responses and align them with concept-relevant prompt tokens through subspace similarity. We then apply three feature-grouping strategies: cluster-based, hierarchical-linkage, and single-token-driven, to identify SAE feature subgroups across all 26 layers. Finally, we amplify the top features in each subgroup and evaluate the resulting generations with a standardized harmfulness judge. Single-token-driven grouping achieves harmfulness comparable to full cluster-based grouping, showing that individual harmful prompt tokens are sufficient to localize vulnerability-relevant SAE feature subgroups without relying on broader cluster-level aggregation. These subgroups appear across early and mid-to-late layers, with stronger concentration in mid-to-late layers, where targeted steering exposes specific model vulnerabilities. Overall, our results suggest that jailbreak susceptibility can be traced to sparse, token-localized SAE feature subgroups, complementing prior accounts based on broad adversarial, refusal, or steering directions.

Nilanjana Das, Mathew Dawit, Aman Chadha +1

UMBC, Maryland, U.S.A. · Apple, California, U.S.A.

LLM Interpretability Sparse Autoencoders LLM Jailbreak Attacks

Apr 23, 2026cs.IR

From Tokens to Concepts: Leveraging SAE for SPLADE

Learned Sparse IR models, such as SPLADE, offer an excellent efficiency-effectiveness tradeoff. However, they rely on the underlying backbone vocabulary, which might hinder performance (polysemicity and synonymy) and pose a challenge for multi-lingual and multi-modal usages. To solve this limitation, we propose to replace the backbone vocabulary with a latent space of semantic concepts learned using Sparse Auto-Encoders (SAE). Throughout this paper, we study the compatibility of these 2 concepts, explore training approaches, and analyze the differences between our SAE-SPLADE model and traditional SPLADE models. Our experiments demonstrate that SAE-SPLADE achieves retrieval performance comparable to SPLADE on both in-domain and out-of-domain tasks while offering improved efficiency.

Yuxuan Zong, Mathias Vast, Basile Van Cooten +2

Sorbonne Université, CNRS, ISIR · Sinequa by ChapsVision · CNRS, Sorbonne Université, ISIR

Learned Sparse Retrieval Sparse Autoencoders Information Retrieval

Apr 20, 2026cs.LG

Towards Understanding the Robustness of Sparse Autoencoders

Large Language Models (LLMs) remain vulnerable to optimization-based jailbreak attacks that exploit internal gradient structure. While Sparse Autoencoders (SAEs) are widely used for interpretability, their robustness implications remain underexplored. We present a study of integrating pretrained SAEs into transformer residual streams at inference time, without modifying model weights or blocking gradients. Across four model families (Gemma, LLaMA, Mistral, Qwen) and two strong white-box attacks (GCG, BEAST) plus three black-box benchmarks, SAE-augmented models achieve up to a 5x reduction in jailbreak success rate relative to the undefended baseline and reduce cross-model attack transferability. Parametric ablations reveal (i) a monotonic dose-response relationship between L0 sparsity and attack success rate, and (ii) a layer-dependent defense-utility tradeoff, where intermediate layers balance robustness and clean performance. These findings are consistent with a representational bottleneck hypothesis: sparse projection reshapes the optimization geometry exploited by jailbreak attacks.

Ahson Saiyed, Sabrina Sadiekh, Chirag Agarwal

University of Virginia · Independent Researcher

Adversarial Attacks on LLMs Jailbreak Robustness Sparse Autoencoders Adversarial Robustness of Language Models Jailbreak Defense

Apr 18, 2026cs.LG

Structural Instability of Feature Composition

Sparse Autoencoders (SAEs) have emerged as a powerful paradigm for disentangling feature superposition in transformer-based architectures, enabling precise control via activation steering. However, the theoretical foundations of compositional steering -- the simultaneous activation of distinct semantic latents -- remain under-explored. The prevailing Linear Representation Hypothesis often abstracts away non-linear interference effects that arise in overcomplete dictionaries. We present a geometric framework for analyzing the instability of feature unions. Modeling the activation space as a high-dimensional sparse cone manifold, we derive an asymptotic compositional-collapse threshold under a spherical dictionary model, characterized by the Gaussian mean width (statistical dimension) of the signal cone. We further show that, in the high-bias regime, ReLU rectification converts microscopic correlation-induced variance fluctuations into a systematic drift that accumulates under composition, yielding interference growth consistent with a ratchet effect. We validate the predicted scaling trends on structured semantic features extracted from CLEVR, where hierarchical correlations accelerate the transition relative to random baselines. Together, our results highlight geometric constraints on the scalability of union-based steering and motivate composition mechanisms that explicitly manage interference beyond naive linear superposition.

Yunpeng Zhou

Whiteknights House, Whiteknights, Reading, RG6 6UR

Feature Superposition Transformer Interpretability Representation Disentanglement Sparse Autoencoders

Apr 16, 2026cs.LG

Improving Sparse Autoencoder with Dynamic Attention

Recently, sparse autoencoders (SAEs) have emerged as a promising technique for interpreting activations in foundation models by disentangling features into a sparse set of concepts. However, identifying the optimal level of sparsity for each neuron remains challenging in practice: excessive sparsity can lead to poor reconstruction, whereas insufficient sparsity may harm interpretability. While existing activation functions such as ReLU and TopK provide certain sparsity guarantees, they typically require additional sparsity regularization or cherry-picked hyperparameters. We show in this paper that dynamically sparse attention mechanisms using sparsemax can bridge this trade-off, due to their ability to determine the activation numbers in a data-dependent manner. Specifically, we first explore a new class of SAEs based on the cross-attention architecture with the latent features as queries and the learnable dictionary as the key and value matrices. To encourage sparse pattern learning, we employ a sparsemax-based attention strategy that automatically infers a sparse set of elements according to the complexity of each neuron, resulting in a more flexible and general activation function. Through comprehensive evaluation and visualization, we show that our approach successfully achieves lower reconstruction loss while producing high-quality concepts, particularly in top-n classification tasks.

Dongsheng Wang, Jinsen Zhang, Dawei Su +1

College of Computer Science and Software Engineering, Shenzhen University, China

Sparse Autoencoders Neural Network Interpretability Sparse Attention

Mar 30, 2026cs.LG

Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalisation

The linear representation hypothesis states that neural network activations encode high-level concepts as linear mixtures. However, under superposition, this encoding is a projection from a higher-dimensional concept space into a lower-dimensional activation space, and a linear decision boundary in the concept space need not remain linear after projection. In this setting, classical sparse coding methods with per-sample iterative inference leverage compressed sensing guarantees to recover latent factors. Sparse autoencoders (SAEs), on the other hand, amortise sparse inference into a fixed encoder, introducing a systematic gap. We show this amortisation gap persists across training set sizes, latent dimensions, and sparsity levels, causing SAEs to fail under out-of-distribution (OOD) compositional shifts. Through controlled experiments that decompose the failure, we identify dictionary learning as the limiting factor (not the inference procedure): SAE-learned dictionaries point in substantially wrong directions, and replacing the encoder with per-sample FISTA on the same dictionary does not close the gap. An oracle baseline proves the problem is solvable with a good dictionary at all scales tested. Our results, including experiments with real LLM activations (Pythia-70M, Gemma-2-2B) reframe the SAE failure as a dictionary learning challenge, not an inference problem, and point to scalable dictionary learning as the key open problem for sparse inference under superposition.

Vitória Barin-Pacela, Shruti Joshi, Isabela Camacho +2

Mila - Québec AI Institute & Université de Montréal · Santa Clara University · Cold Spring Harbor Laboratory

Sparse Autoencoders Sparse Coding Dictionary Learning Compositional Generalization

Mar 18, 2026cs.SD

Towards Interpretable Framework for Neural Audio Codecs via Sparse Autoencoders: A Case Study on Accent Information

Neural Audio Codecs (NACs) are widely adopted in modern speech systems, yet how they encode linguistic and paralinguistic information remains unclear. Improving the interpretability of NAC representations is critical for understanding and deploying them in sensitive applications. Hence, we employ Sparse Autoencoders (SAEs) to decompose dense NAC representations into sparse, interpretable activations. In this work, we focus on a challenging paralinguistic attribute-accent-and propose a framework to quantify NAC interpretability. We evaluate four NAC models under 16 SAE configurations using a relative performance index. Our results show that DAC and SpeechTokenizer achieve the highest interpretability. We further reveal that acoustic-oriented NACs encode accent information primarily in activation magnitudes of sparse representations, whereas phonetic-oriented NACs rely more on activation positions, and that low-bitrate EnCodec variants show higher interpretability.

Shih-Heng Wang, Tiantian Feng, Aditya Kommineni +4

University of Southern California, USA

Neural Audio Codecs Sparse Autoencoders Neural Network Interpretability Neural Encoding

Mar 3, 2026cs.LG

Step-Level Sparse Autoencoder for Reasoning Process Interpretation

Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning patterns remain too complicated to analyze. While Sparse Autoencoders (SAEs) have emerged as a powerful tool for interpretability, existing approaches predominantly operate at the token level, creating a granularity mismatch when capturing more critical step-level information, such as reasoning direction and semantic transitions. In this work, we propose step-level sparse autoencoder (SSAE), which serves as an analytical tool to disentangle different aspects of LLMs' reasoning steps into sparse features. Specifically, by precisely controlling the sparsity of a step feature conditioned on its context, we form an information bottleneck in step reconstruction, which splits incremental information from background information and disentangles it into several sparsely activated dimensions. Experiments on multiple base models and reasoning tasks show the effectiveness of the extracted features. By linear probing, we can easily predict surface-level information, such as generation length and first token distribution, as well as more complicated properties, such as the correctness and logicality of the step. These observations indicate that LLMs should already at least partly know about these properties during generation, which provides the foundation for the self-verification ability of LLMs. Our code is available at https://github.com/Miaow-Lab/SSAE.

Xuan Yang, Jiayu Liu, Yuhang Lai +3

Department of Data Science, City University of Hong Kong · Hong Kong Institute of AI for Science, City University of Hong Kong · Li Auto Inc +1

LLM Interpretability Sparse Autoencoders LLM Reasoning

Feb 16, 2026cs.LG

SynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic Data

Improving Sparse Autoencoders (SAEs) requires benchmarks that can precisely validate architectural innovations. Current LLM-based SAE benchmarks are too noisy to differentiate architectural improvements, while commonly used synthetic-data experiments are too small-scale, unstandardized, and unrealistic to be meaningful. We introduce SynthSAEBench, a benchmark and toolkit for evaluating SAEs against large-scale synthetic data with realistic feature characteristics including correlation, hierarchy, and superposition, while providing ground-truth features and firings. SynthSAEBench acts as a controlled lower-bound test: SAE architectures that fail when the Linear Representation Hypothesis holds by construction have little hope on real LLMs. The benchmark reproduces known LLM SAE phenomena including the disconnect between reconstruction and latent quality, poor SAE probing, and a precision-recall trade-off mediated by L0, demonstrating that SynthSAEBench findings reproduce results on LLM SAEs. We further identify a novel failure mode: Matching Pursuit SAEs exploit superposition noise to improve reconstruction without learning ground-truth features, suggesting more expressive encoding procedures can easily overfit. SynthSAEBench complements LLM benchmarks with ground-truth features and controlled ablations for diagnosing SAE failure modes, while providing a clear target for SAE architecture work.

David Chanin, Adrià Garriga-Alonso

University College London · 2MATS · 3Decode Research

Sparse Autoencoders Synthetic Benchmark Generation Synthetic Data Evaluation

Feb 12, 2026cs.CR

Sparse Autoencoders are Capable LLM Jailbreak Mitigators

Jailbreak attacks remain a persistent threat to large language model safety. We propose Context-Conditioned Delta Steering (CC-Delta), an SAE-based defense that identifies jailbreak-relevant sparse features by comparing token-level representations of the same harmful request with and without jailbreak context. Using paired harmful/jailbreak prompts, CC-Delta selects features via statistical testing and applies inference-time mean-shift steering in SAE latent space. Across four aligned instruction-tuned models and twelve jailbreak attacks, CC-Delta achieves comparable or better safety-utility tradeoffs than baseline defenses operating in dense latent space. In particular, our method clearly outperforms dense mean-shift steering on all four models, and particularly against out-of-distribution attacks, showing that steering in sparse SAE feature space offers advantages over steering in dense activation space for jailbreak mitigation. Our results suggest off-the-shelf SAEs trained for interpretability can be repurposed as practical jailbreak defenses without task-specific training.

Yannick Assogba, Jacopo Cortellazzi, Javier Abad +3

1Apple · 2ETH Zurich

Sparse Autoencoders LLM Jailbreak Attacks Jailbreak Defense Activation Steering

Feb 3, 2026cs.LG

Variational Sparse Paired Autoencoders (vsPAIR) for Inverse Problems and Uncertainty Quantification

Inverse problems are fundamental to many scientific and engineering disciplines; they arise when one seeks to reconstruct hidden, underlying quantities from noisy measurements. Many applications demand not just point estimates but interpretable uncertainty. Providing fast inference alongside uncertainty estimates remains challenging yet desirable in numerous applications. We propose the Variational Sparse Paired Autoencoder (vsPAIR) to address this challenge. The architecture pairs a standard VAE encoding observations with a sparse VAE encoding quantities of interest (QoI), connected through a learned latent mapping. The variational structure enables uncertainty estimation, the paired architecture encourages interpretability by anchoring QoI representations to clean data, and sparse encodings provide structure by concentrating information into identifiable factors rather than diffusing across all dimensions. To validate the effectiveness of our proposed architecture, we conduct experiments on blind inpainting, computed tomography (CT), and initial-condition inference for the heat equation, demonstrating that vsPAIR is a capable inverse problem solver that can provide interpretable and structured uncertainty estimates.

Jack Michael Solomon, Rishi Leburu, Matthias Chung

Emory University Department of Mathematics

Variational Autoencoders Uncertainty Quantification Autoencoders Sparse Autoencoders Inverse Problems

Feb 2, 2026cs.AI

Beyond Dense States: Sparse Transcoders as Causally Testable Operators for LLM Latent Reasoning

Latent reasoning reduces the token-generation cost of chain-of-thought reasoning by replacing explicit intermediate tokens with continuous latent transitions. However, existing latent reasoning methods usually rely on dense and entangled transitions, making their reasoning trajectories difficult to inspect or intervene on. We introduce LSTR (Latent Sparse Transcoder Reasoning), a framework that turns sparse transcoders from post-hoc diagnostic tools into in-loop, intervenable transition components for latent reasoning. At each latent step, a Latent Transition Transcoder (LTT) combines a linear skip path with a Top-k sparse innovation path, exposing a small set of active sparse features. Under matched compression settings, LSTR offers a mechanistically inspectable alternative to dense latent reasoning. On GSM8K-Aug, ablating only a few top-active sparse features reduces accuracy by up to 16.5%, whereas analogous interventions have much smaller effects in dense latent baselines. These results indicate that the active sparse features are causally involved in the latent transition process, rather than merely post-hoc descriptors. Additional experiments on mathematical benchmarks and StrategyQA suggest that sparse latent transitions can preserve the compression benefits of latent reasoning while making the resulting trajectories more inspectable and intervenable.

Yadong Wang, Haodong Chen, Yu Tian +3

Nanjing University of Aeronautics and Astronautics · State Key Laboratory of Ocean Sensing, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou, 311215, China · Security Capability Center

Sparse Autoencoders Continuous Latent Reasoning Causal Interventions in Language Models LLM Reasoning Latent Reasoning Latent CoT Reasoning

Nov 21, 2025cs.CV

Towards Open-Ended Visual Scientific Discovery with Sparse Autoencoders

Foundation models in several scientific domains, including visual domains, learn representations that capture complex semantics from their respective fields. Despite this, most existing applications focus on pre-specified concepts or targets, excelling at confirmation but not open-ended discovery of unknown patterns. We study whether sparse autoencoders (SAEs) with heuristic feature ranking can provide a practical methodology for surfacing candidate visual features from vision foundation models for scientific discovery without concept-specific supervision. We evaluate this approach in three stages: (1) general-purpose concept rediscovery, (2) domain-specific concept rediscovery, and (3) question-driven feature ranking. On ADE20K, SAEs outperform baseline methods (

k

-means, PCA, SemiNMF) across most downstream metrics for concept rediscovery. On FishVista, the same approach recovers fine-grained fish anatomical features without concept supervision. Finally, on Heliconius butterflies, a heuristic based on the Mann-Whitney

U

statistic consistently surfaces features corresponding to real diagnostic keys between mimic subspecies. Together, these results show that SAEs with heuristic ranking can efficiently learn and surface semantic structure in vision foundation model representations. We view this as a methodological prerequisite for open-ended visual scientific discovery: the present experiments validate feature surfacing and ranking through rediscovery, while prospective discovery of previously unknown scientific phenomena remains future work.

Jacob Beattie, Samuel Stevens, Neil Rosser +2

The Ohio State University

Vision Foundation Models Sparse Autoencoders Sparse Coding

Aug 22, 2025cs.LG

Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders

Sparse Autoencoders (SAEs) extract features from LLM internal activations, meant to correspond to interpretable concepts. A core SAE training hyperparameter is L0: how many SAE features should fire per token on average. Existing work compares SAE algorithms using sparsity-reconstruction tradeoff plots, implying L0 is a free parameter with no inherently correct value aside from its effect on reconstruction. In this work we study the effect of L0 on SAEs, and show that if L0 is not set correctly, the SAE fails to disentangle the underlying features of the LLM. If L0 is too low, the SAE will mix correlated features to improve reconstruction. If L0 is too high, the SAE finds degenerate solutions that also mix features. Further, we present a proxy metric that can help guide the search for the correct L0 for an SAE on a given training distribution. We show that our method finds the correct L0 in toy models and coincides with peak sparse probing performance in LLM SAEs. We find that most commonly used SAEs have an L0 that is too low. Our work shows that practitioners must set L0 correctly to train SAEs with monosemantic features.

David Chanin, Adrià Garriga-Alonso

University College London · MATS Research

Activation Sparsity LLM Interpretability Representation Disentanglement Sparse Autoencoders Sparse Coding Hyperparameter Optimization

Jul 15, 2025cs.CL

Sparse Autoencoders Can Capture Language-Specific Concepts Across Diverse Languages

Understanding the multilingual mechanisms of large language models (LLMs) provides insight into how they process different languages, yet this remains challenging. Existing studies often focus on individual neurons, but their polysemantic nature makes it difficult to isolate language-specific units from cross-lingual representations. To address this, we explore sparse autoencoders (SAEs) for their ability to learn monosemantic features that represent concrete and abstract concepts across languages in LLMs. While some of these features are language-independent, the presence of language-specific features remains underexplored. In this work, we introduce

\textit{SAE-LAPE}

, a method based on feature activation probability, to identify language-specific features within the feed-forward network. We find that many such features predominantly appear in the middle to late layers of the model and are interpretable. These features influence the model's multilingual performance and language output, and can be used for language identification with performance comparable to fastText, along with more interpretability. Our code and complete figures are available at https://github.com/LyzanderAndrylie/language-specific-features.

Lyzander Marciano Andrylie, Inaya Rahmanisa, Mahardika Krisna Ihsani +3

Faculty of Computer Science, Universitas Indonesia · Department of Natural Language Processing, MBZUAI

Multilingual Language Models Representation Learning Language Identification LLM Interpretability Sparse Autoencoders

Jun 30, 2025cs.LG

Position: Use Sparse Autoencoders to Discover Unknowns

While sparse autoencoders (SAEs) have generated significant excitement, a series of negative results have added to skepticism about their usefulness. Here, we establish a conceptual distinction that reconciles competing narratives surrounding SAEs. We argue that even if SAEs may be less effective for \textit{acting on known concepts}, SAEs are especially powerful tools for \textit{discovering unknown concepts}. This distinction separates existing negative results from positive results, and suggests several classes of SAE applications. Specifically, we outline use cases for SAEs in (i) ML interpretability, explainability, fairness, auditing, and safety, and (ii) social and health sciences.

Kenny Peng, Rajiv Movva, Jon Kleinberg +2

1Cornell University · 2UC Berkeley

Explainable Artificial Intelligence Sparse Autoencoders Neural Network Interpretability

Jun 24, 2025cs.LG

Cross-Layer Discrete Concept Discovery for Interpreting Language Models

Interpreting language models remains challenging due to the existence of residual stream, which linearly mixes and duplicates features across adjacent layers, causing single-layer analyses to miss this cross-layer structure. Cross-layer sparse autoencoders (SAEs) address layer mixing but operate in continuous space, where concepts split across many neurons without clear boundaries. We introduce Cross-Layer Vector Quantized-Variational Autoencoder (CLVQ-VAE), a novel framework which maps representations from a lower layer to a higher layer through a discrete vector-quantization bottleneck, collapsing duplicated residual-stream features into compact, interpretable concept vectors. Our approach combines top-k temperature-based sampling with exponential moving average (EMA) codebook updates, providing controlled exploration of the discrete latent space while maintaining codebook diversity. Across both encoder- and decoder-based models on ERASER-Movie, Jigsaw, and AGNews, CLVQ-VAE outperforms clustering, single-layer vector quantized-variational autoencoder (VQ-VAE), and sparse autoencoder (SAE) baselines across three evaluation axes: removing identified concepts drops downstream probe accuracy by up to 93%, LLM judges rank our concepts first in 66.7% of comparisons, and human annotators recover model predictions from our visualizations with 78% accuracy versus 54% for clustering.

Ankur Garg, Xuemin Yu, Hassan Sajjad +1

Variational Autoencoders LLM Interpretability Vector-Quantized Variational Autoencoder Sparse Autoencoders Language Model Probing

May 28, 2025cs.LG

Kronecker Factorization Improves Efficiency and Interpretability of Sparse Autoencoders

Sparse Autoencoders (SAEs) decompose language-model activations into sparse, interpretable features, but standard encoders usually treat the latent dictionary as a flat set of independent coordinates, leaving hierarchy and feature interactions to emerge only implicitly. We propose KronSAE, a design that factorizes the latent space into heads and forms post-latent features as pairwise compositions of lower-dimensional pre-latents using mAND, a differentiable AND-like interaction. This imposes a compositional co-activation prior while remaining compatible with standard SAE objectives and variants such as TopK, Matryoshka, and Switch SAEs. KronSAE matches strong baselines on the EV-FLOPs frontier, improves interpretability of the latents, better captures the underlying correlated feature structure, and reduces encoder computational cost as an additional benefit. Code is available at https://github.com/corl-team/kronsae.

Vadim Kurochkin, Yaroslav Aksenov, Daniil Laptev +2

T-Tech

Representation Learning Activation Sparsity Hierarchical Representation Learning Sparse Autoencoders Mechanistic Interpretability Sparse Coding+1

Date pendingcs.CL

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization

Although Sparse Autoencoders (SAEs) have mitigated the opacity of large language models (LLMs) by decomposing dense representations into sparse features, explaining these features still remains a central challenge. Current explanation methods, however, typically operate within an open-loop paradigm, failing to leverage mechanistic feedback for further refinement. In this paper, we propose SAEExplainer, a training framework that utilizes activation scores as an objective reward signal to train the model for self-correction and iterative bootstrapping. By iteratively verifying and correcting foundational explanations through a two-round optimization process, SAEExplainer achieves continuous improvement in its explanatory capabilities. This mechanism significantly reduces explanation hallucinations and reinforces causal triggering patterns. Extensive experiments demonstrate our approach improves upon established baselines across most metrics, especially in causal triggering and discriminative activation. The code is available at https://github.com/he-jingyi/SAEExplainer.

Jingyi He, Haiyan Zhao, Ruxue Shi +4

The Chinese University of Hong Kong, Shenzhen · Shanghai Jiao Tong University · NJIT +2

LLM Interpretability Sparse Autoencoders Mechanistic Interpretability

Date pendingcs.AI

SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?

While research on recursive self-improvement (RSI) has predominantly automated model training pipelines, reliable autonomous development demands a missing pillar: post-hoc monitoring and auditing to understand what models learn and ensure safe alignment. Mechanistic interpretability tools are essential to bridge this gap, among which Sparse Autoencoders (SAEs) serve as a cornerstone by isolating interpretable features for model inspection and steering. In this paper, we introduce SAEScientist-Bench to evaluate whether AI agents can act as scientists utilizing SAE tools for autonomous mechanistic discovery. Given a target concept, an agent designs contrastive probes and navigates a Gemma Scope dictionary of 131K+ features in Gemma-2-9B-IT to discover the optimal feature, evaluated against curated expert reference features anchored on Neuronpedia across activation rank, concept selectivity on contrastive texts, and causal steering. Across 10 agent configurations and 20 tasks, frontier agents demonstrate genuine discovery capabilities and lead different evaluation dimensions, but remain well behind the expert baseline, approaching expert levels on separating target concepts from contrastive controls while lagging substantially in causal generation steering. Further analysis reveals that although agents can design contrasts to rule out spurious candidates, they frequently misinterpret experimental measurements. These results establish experimental model understanding as a measurable capability for closed-loop autonomous AI R&D. Our code is available at https://github.com/Trae1ounG/SAEScientist.

Yuqiao Tan, Shizhu He, Jun Zhao +1

The Key Laboratory of Cognitive Intelligence, Institute of Automation, CAS · School of Artificial Intelligence, University of Chinese Academy of Sciences

AI Agent Evaluation Sparse Autoencoders Mechanistic Interpretability AI Agent Benchmarks Autonomous Scientific Discovery