Sparse Autoencoders

Also known as SAE

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
View on map

Latest papers 149

All topics
CardsList

  1. Disentangling Linguistic and Paralinguistic Information with Routed Sparse Autoencoders

    Oct 7, 2026Beimnet Bekele Guta, Xiaoyu Yang, Guangzhi Sun +1Disentangled Representation LearningSelf-Supervised Speech Representation Learning

    Department of Engineering, University of Cambridge, Cambridge, UK

  2. Inference and learning in sparse autoencoders as natural gradient flow

    Oct 5, 2026Hadi Vafaii, Tejas Rao, David Chanin +6Gradient DescentSparse Autoencoders

    Astera Institute · UC Berkeley · UCL +2

  3. Backdooring Sparse Autoencoders

    Oct 5, 2026Enrico Ahlers, Daniel Passon, Tobias Kiecker +2LLM Backdoor AttacksAdversarial Attacks

    Humboldt-Universität zu Berlin Berlin, Germany

  4. A Testable Theory of Atomic Features

    Oct 5, 2026Kenny Peng, Jon Kleinberg, Nikhil GargSparse AutoencodersRepresentation Geometry in Language Models

    Cornell University

  5. Generative modeling of intrinsically disordered protein regions by reinforcing sparse autoencoder features

    Oct 1, 2026Jason X. Liu, Sebastian Ibarraran, Frank Hu +7Autoregressive Language ModelingSparse Autoencoders

    Stanford University

  6. From Isolated Feature to Orbits: Discovering Music Concepts via Multi-SAE Alignment

    Oct 1, 2026Liwei Lin, Gus XiaRepresentation LearningSparse Autoencoders

    Computer Science Department, NYU Shanghai · Machine Learning Department, MBZUAI

  7. D-Scope: Decomposing and Steering Diffusion Transformers with Sparse Autoencoders

    Sep 30, 2026Xinyue Xu, Jiahao Zhang, Lijie Hu +2Transformer InterpretabilityDiffusion Transformer

    Pivotal Research · Mohamed bin Zayed University of Artificial Intelligence · Schmidt Sciences +2

  8. Active Budget Can Kill Sensitivity: Diagnosing and Repairing TopK Sparse Autoencoder Reliability

    Sep 29, 2026Zhenting Huang, Bo Jiang, Junnan Liu +2Activation SparsityLLM Interpretability

    Beihang University · Monash University · Zhongguancun Laboratory

  9. Beyond Token Scale: Chunk-Level Sparse Autoencoders for Reliable Semantic Feature Discovery

    Sep 28, 2026Xu Wang, Yifan Yang, TingHao YU +1Representation LearningLLM Interpretability

    The University of Hong Kong · Hunyuan Team, Tencent

  10. From Input to Output: A Flexible Agent for Dual-End Interpretation of Sparse Autoencoder Features

    Sep 28, 2026Dewen Liu, Zixuan Li, Jonathan Pan +4Sparse AutoencodersMechanistic Interpretability

    Tsinghua University · Fudan University · University of Edinburgh

  11. Verifying the Linear Representation Hypothesis: How Interpretable Are Vision SAEs?

    Sep 28, 2026Teodor Chiaburu, Franz Motzkus, Frank Haußer +1Linear Representation HypothesisSparse Autoencoders

    Fraunhofer SIT · ATHENE National Research Center for Applied Cybersecurity · AUMOVIO +3

  12. When Is an SAE Feature Interpretable? A Validation Ladder for EEG Foundation Models

    Sep 28, 2026Yucong Cao, Chenqi Li, Tingting ZhuPerturbation-Based Feature AttributionSparse Autoencoders

    Department of Engineering Science University of Oxford

  13. Towards Interpretable Framework for Neural Audio Codecs via Sparse Autoencoders: Exploration toward Age, Gender, and Accent Steering

    Sep 28, 2026Shih-Heng Wang, Tiantian Feng, Aditya Kommineni +4Neural Audio CodecsSparse Autoencoders

    University of Southern California, USA

  14. Parts-of-Speech as Emergent Categories in SAE Latent Space

    Sep 24, 2026Alessandro Bondielli, Lucia Passaro, Serena Auriemma +1Sparse AutoencodersRepresentation Geometry in Language Models

    CoLingLab, Department of Philology, Literature and Linguistics, University of Pisa · Department of Computer Science, University of Pisa

  15. Local Sparsity Enables Unsupervised LLM Safety Detection

    Sep 17, 2026Xin Chen, Gil Kur, Alexander Shevchenko +1Sparse AutoencodersLLM Safety

    ETH Zürich

  16. What Does an LLM Learn from Reinforcement Learning? A Mechanistic Interpretability Perspective with Fixed-SAE Track

    Sep 14, 2026Lingheng Du, Yiming Tang, Xufeng Duan +1RL for Language ModelsSparse Autoencoders

    Peking University · National University of Singapore · The Chinese University of Hong Kong

  17. Where Decoder Cosine Similarity Fails for SAE Feature Flow Discovery

    Sep 14, 2026Hendrik Droste, Christian Medeiros Adriano, Kathrin Korte +1Transformer InterpretabilitySparse Autoencoders

    Hasso Plattner Institute, Germany · IT University of Copenhagen, Denmark

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

    Sep 9, 2026Alexis D. PlascenciaFeature SuperpositionRepresentation Disentanglement

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

    Sep 9, 2026Una Joh, Bei YuTopic ModelingSparse Autoencoders

    School of Information Studies Syracuse University

  20. Tracing Stereotypes from Representation to Output in Multilingual LLMs

    Sep 8, 2026Ariun-Erdene Tumurchuluun, Yusser Al Ghussin, Pinzhen Chen +2Multilingual Language ModelsSocial Bias in Language Models

    Saarland University, Saarland Informatics Campus · German Research Center for Artificial Intelligence (DFKI) · Queen’s University Belfast +1

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

    Sep 3, 2026Xinghao Wang, Dong Li, Wei Yu +5Video Diffusion ModelsSparse Autoencoders

    University of Science and Technology of China, Hefei, China · HiDream.ai Inc. · Anhui Province Key Laboratory of Digital Security, China

  22. Exploring Sparse Autoencoders in Text-Based Causal Confounding Adjustment

    Sep 1, 2026Mian Zhong, Katherine A. Keith, Anjalie FieldCausal Effect EstimationSparse Autoencoders

    Johns Hopkins University · Williams College / Cohere · Cohere

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

    Aug 13, 2026Weihan Meng, Hongzhu Guo, Yi Jing +5LLM InterpretabilitySparse Autoencoders

    Tsinghua University · Peking University · Fudan University

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

    Aug 13, 2026Valentin NoëlSparse AutoencodersCausal Interventions in Language Models

    Devoteam

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

    Aug 11, 2026Nikolai Bolik, Lennart Stöpler, Artur AndrzejakRepresentation LearningLLM Interpretability

    Heidelberg University

  26. Measuring Semantic Abstractness of SAE Features via Nonlocality

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

    Rudolf Peierls Centre for Theoretical Physics, University of Oxford · Leinweber Institute for Theoretical Physics, Stanford University

  27. Post-Hoc Sparse Coding of Latent Communication Between Vision-Language Model Agents

    Aug 10, 2026Di Wu, Xiaohui ZhuSparse AutoencodersMultimodal Token Compression

    Xi’an Jiaotong-Liverpool University

  28. Multimodal Model Diffing for Feature Discovery and Control

    Aug 10, 2026Hunar Batra, Lachin Naghashyar, Ashkan Khakzar +4Sparse AutoencodersMultimodal Model Interpretability

    University of Oxford · Microsoft

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

    Aug 9, 2026Julien Guinot, Alain Riou, Elio Quinton +1Feature AttributionSparse Autoencoders

    Music & Audio Machine Learning Lab, Universal Music Group, London, U.K. · Centre for Digital Music, Queen Mary University of London, U.K.

  30. Interpretable GOHR Agents via Sparse Autoencoders

    Jul 27, 2026Shiwei Tan, Yusong Zhao, Weiyi Qin +6Transformer InterpretabilitySparse Autoencoders

    1Rutgers University · 3Paul B Kantor Consultant · University of Illinois Urbana-Champaign