Sparse Autoencoders

Ask about this topic

Recent momentum

-60%

8 papers in the last 28 days · 0.2% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-14

7 new papers

A weekly snapshot of new work published in Sparse Autoencoders.

153 papers

Latest in Sparse Autoencoders

Open your feed →
CardsList

  1. High-probability guarantees for linear accessibility in feature superposition

    Sep 10, 2026Enrico VompaSuperpositionSparse Autoencoders

  2. A Dominant Diffuse Phase in the Sparse Autoencoder Phase Diagram

    Sep 9, 2026Alexis D. PlascenciaSparse AutoencodersFeature Learning

  3. Beyond Top Words: MonoTM for Topic Modeling with Interpretable Monosemantic Features

    Sep 9, 2026Una Joh, Bei YuTopic ModelingSparse Autoencoders

  4. Key Path Identification for Resolving Knowledge Conflicts via SAE-based Steering

    Sep 8, 2026Wenbo Zhang, Zhongxiang Sun, Zhiguang Han +1Knowledge ConflictsSteering

  5. LLM Layers Immediately Correct Each Other

    Sep 7, 2026Arjun Patrawala, Jiahai Feng, Erik Jones +1Model ActivationsResidual Stream

  6. LLM Forensics: Where Do Backdoors Hide? Localizing and Controlling Trigger Mechanisms with Sparse Autoencoders

    Sep 7, 2026Wissam Antoun, Francis Kulumba, Théo Lasnier +2Backdoor AttacksLarge Language Model Safety

  7. EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders

    Sep 3, 2026Xinghao Wang, Dong Li, Wei Yu +5Concept ErasureText-To-Image Diffusion Models

  8. When Safety Speaks a Language: A Mechanistic Analysis of Safety-Language Identity Entanglement in LLMs

    Aug 30, 2026Apoorva Upadhyaya, Sandipan SikdarMultilingual SafetyLarge Language Model Safety

  9. SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization

    Aug 13, 2026Weihan Meng, Hongzhu Guo, Yi Jing +5Sparse AutoencodersVerbalization

  10. Where You Measure Decides What You Measure: Position Selection in Ablation-Based SAE Evaluation

    Aug 13, 2026Valentin NoëlImproving Sparse AutoencodersSparse Autoencoders

  11. Probing and steering biology across Boltz-1s trunk-diffusion boundary

    Aug 11, 2026Piotr Jedryszek, Tongmeng Xie, Adam Winnifrith +5ProteinFeature Alignment

  12. Beyond a Bag of Features: Set-Level Instability in Sparse Autoencoders

    Aug 11, 2026Nikolai Bolik, Lennart Stöpler, Artur AndrzejakSparse AutoencodersLatent Space

  13. Measuring Semantic Abstractness of SAE Features via Nonlocality

    Aug 11, 2026Chuqiao Lin, Shivaji Sondhi, Xiao-Liang QiSparse AutoencodersMechanistic Interpretability

  14. Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability

    Aug 10, 2026Ashim Dhor, Pin-Yu ChenMechanistic InterpretabilityModel Interpretability Methods

  15. Multimodal Model Diffing for Feature Discovery and Control

    Aug 10, 2026Hunar Batra, Lachin Naghashyar, Ashkan Khakzar +4Large Multimodal ModelsSparse Autoencoders

  16. One Adapter Pair per Model: A Universal Activation Interface for Language Models

    Aug 10, 2026Su-Hyeon Kim, Jiwan Mun, Yo-Sub HanModel ActivationsProtein Language Model

  17. Steering dense music retrieval with open-vocabulary concept discovery

    Aug 9, 2026Julien Guinot, Alain Riou, Elio Quinton +1Sparse AutoencodersMultimodal Embeddings

  18. Thinking vs. NoThinking: Towards Interpreting Reasoning Mechanisms of Large Language Models via Sparse Autoencoders

    Aug 8, 2026Bo Cheng, Qiaolin Lu, Yi Chang +1ThinkingSparse Autoencoders

  19. "Many Are My Names": The Anatomy of the Assistant and Its Personas via Sparse Autoencoders

    Aug 8, 2026Adelaide Danilov, Aria Nourbakhsh, Oleksandr Marchenko Breneur +1PersonasRole-Playing

  20. CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits

    Aug 6, 2026Mehrshad Saadatinia, Parsa Razmara, Ardalan Aryashad +2Linear Activation SteeringSteering

  21. Strengthening Target-Language Features: SAE-Based Steering for Multilingual Inference

    Aug 5, 2026Hongsheng Wang, Philipp KoehnMultilingual Language ModelsProtein Language Model

  22. Explaining Image Similarity with Automatically Extracted Concept Activation Vectors

    Jul 30, 2026Isaac Roberts, Petra Bevandic, Alexander Schulz +1Semantic Similarity MetricsSaliency

  23. Interpretable GOHR Agents via Sparse Autoencoders

    Jul 27, 2026Shiwei Tan, Yusong Zhao, Weiyi Qin +6Sparse AutoencodersAgent Decisions

  24. Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects

    Jul 27, 2026Phu Gia Hoang, Anwoy Chatterjee, Tanmoy Chakraborty +2Improving Sparse AutoencodersSparse Autoencoders

  25. Scaling Interpretable Transformers with Parity Bottleneck Layers

    Jul 22, 2026Andrew Mack, Kraig Yuheng Tou, Mark Henry +2Sparse AutoencodersModel Interpretability Methods

  26. Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects

    Jul 22, 2026Seonglae Cho, Zekun Wu, Kleyton Da Costa +3Sparse AutoencodersModel Activations

  27. Causal dictionary learning reveals and validates transcription-factor binding features in genomic language models

    Jul 21, 2026Sarwan AliTranscriptomicsLearnable Probe Vectors

  28. Measuring Monosemanticity in Sparse Autoencoders via Latent Activation Coherence

    Jul 20, 2026Katarzyna Filus, Sebastian PokucińskiSparse AutoencodersMechanistic Interpretability

  29. Decoder-Preserving Sparse Autoencoders: Which Readouts Survive Sparse Compression?

    Jul 19, 2026Aniket DeshpandeImproving Sparse AutoencodersSparse Autoencoders

  30. Persistent Sparse Autoencoders: Learning Feature-Specific Timescales in Language Model Representations

    Jul 19, 2026Haoyan Luo, Mateo Espinosa Zarlenga, Mateja JamnikSparse AutoencodersImproving Sparse Autoencoders

  31. From Geometric Recovery to Causal Validation: A Reproducible Audit of Sparse Autoencoder Features, from Superposition Geometry to Causal Inertness

    Jul 13, 2026Mohamed Abdessalem BalImproving Sparse AutoencodersSparse Autoencoders

  32. Sparse Autoencoders for Interpretable Out-of-Distribution Detection

    Jul 13, 2026Ayush Karmacharya, Luke Luschwitz, Lucia Romero +2Out-Of-Distribution Detection PerformanceOut-Of-Distribution

  33. When Are Sparse Feature Interventions Actually Localized? Matched Evaluation for SAE-Based Safety Control

    Jul 11, 2026Daming LuoAI Safety AlignmentSparse Autoencoders

  34. When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities

    Jul 9, 2026Weiduo Liao, Yunqiao Yang, Ying WeiImproving Sparse AutoencodersSparse Autoencoders

  35. Cross-seed explainability using Procrustes-conditioned Joint End-to-end Top-K Sparse Autoencoders

    Jul 9, 2026Bendegúz Váradi, Zoltán KmettyImproving Sparse AutoencodersSparse Autoencoders

  36. A Coin Flip Per Token: Bernoulli Sparse Steering of Large Language Models

    Jul 6, 2026Nima Eshraghi, Lovedeep Gondara, Yuqing Huang +5Linear Activation SteeringSteering

  37. TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models

    Jul 6, 2026Riccardo Renzulli, Gabriele Spadaro, Shruthi Gowda +2Visual Token PruningSparse Autoencoders

  38. Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability

    Jul 2, 2026Rodrigo Mendoza-SmithImproving Sparse AutoencodersSparse Autoencoders

  39. Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders

    Jul 1, 2026Zihao Qi, Christopher EarlsQuantum LearningMany-Body Physics

  40. Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models

    Jun 30, 2026Enrico Cassano, Riccardo Renzulli, Rayyan Ahmed +2Diffusion ModelsSparse Autoencoders

  41. C^{2}R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders

    Jun 29, 2026Haoran Jin, Xiting Wang, Shijie Ren +2Sparse AutoencodersRegularization Methods

  42. Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse Autoencoders

    Jun 29, 2026Chungpa Lee, Jihoon Kwon, Kyle Min +1Sparse AutoencodersHeterogeneity

  43. Turn-Averaged SAEs for Feature Discovery and Long-Context Attribution

    Jun 26, 2026Kevin Der, Harish Kamath, Ben ThompsonSparse AutoencodersImproving Sparse Autoencoders

  44. VASAE: Naming SAE Dictionary Directions with Vocabulary-Aligned Anchoring

    Jun 26, 2026Kairui Zhang, Ziwen Yu, Zahraa S. Abdallah +1Improving Sparse AutoencodersSparse Autoencoders

  45. PairSAE: Mechanistic Interpretability from Pair Representations in Protein Co-Folding

    Jun 25, 2026Giosue Migliorini, Aristofanis Rontogiannis, Grigori Guitchounts +3ProteinSparse Autoencoders

  46. Beyond the Hard Budget: Sparsity Regularizers for More Interpretable Top-k Sparse Autoencoders

    Jun 25, 2026Nathanaël Jacquier, Maria Vakalopoulou, Mahdi S. HosseiniImproving Sparse AutoencodersSparse Autoencoders

  47. Forecasting With LLMs: Improved Generalization Through Feature Steering

    Jun 25, 2026Humzah Merchant, Bradford LevyLLM Reasoning MethodsLookahead

  48. From Weights to Features: SAE-Guided Activation Regularization for LLM Continual Learning

    Jun 25, 2026Evan Ning, Wei Xue, Dong Lou +1Catastrophic ForgettingSparse Autoencoders

  49. Discovering Millions of Interpretable Features with Sparse Autoencoders

    Jun 25, 2026XinYang He, Wei Wang, Bing Zhao +5Sparse AutoencodersQwen3

  50. At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer Generalization

    Jun 24, 2026Praneet Suresh, Jack Stanley, Sonia Joseph +2Out-Of-DistributionLarge Language Model Safety

  51. Steering Vision-Language Models with Joint Sparse Autoencoders

    Jun 24, 2026Huizhen Shu, Xuying Li, Hongxu Lin +2Improving Sparse AutoencodersSparse Autoencoders

  52. Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations

    Jun 23, 2026Jonas Klotz, Cassio F. Dantas, Pallavi Jain +2Sparse AutoencodersModel Interpretability Methods

  53. What Does a Chemical Language Model Know About Molecules?

    Jun 22, 2026Christian Kenneth, Etowah Adams, Liam Bai +1Molecular Structure ElucidationProtein Language Model

  54. Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?

    Jun 22, 2026Nils Grandien, David Steinmann, Felix Friedrich +1Sparse AutoencodersHierarchical

  55. Extraction and Analysis of Multimodal Concepts in Vision Language Models through Sparse Autoencoders

    Jun 19, 2026Sergio Lanza, Jae Hee Lee, Stefan WermterKnowledge-Based Visual Question AnsweringSparse Autoencoders

  56. Aligning Sentence Embeddings to Human Concepts via Sparse Autoencoders

    Jun 19, 2026Wonseok Shin, Songkuk KimRetrieval LayerRetrieval-Augmented Generation

  57. SAERec: Constructing Fine-grained Interpretable Intents Priors via Sparse Autoencoders for Recommendation

    Jun 17, 2026Jiangnan Xia, Xuansheng Wu, Yu Yang +2Recommendation QualityRecommendation

  58. From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability

    Jun 16, 2026Dibyanayan Bandyopadhyay, Asif EkbalSparse AutoencodersModel Interpretability Methods

  59. SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior

    Jun 16, 2026Mingyue Cui, Linghui Shen, Xingyi YangSparse AutoencodersCausal Intervention

  60. Scalable Circuit Learning for Interpreting Large Language Models

    Jun 15, 2026Naiyu Yin, Dennis Wei, Tian Gao +3Mechanistic InterpretabilityCircuits