# SAE features and their applications

Area: [Mechanistic interpretability](https://mlsanity.com/mechinterp/index.md). HTML: https://mlsanity.com/mechinterp/sae-features-and-their-applications/

## Key facts

- SAE features and their applications: 231 papers on arXiv since 2022 (data through 14 Oct 2026).
- 171 of its 231 mapped papers (74%) cite “Sparse Autoencoders Find Highly Interpretable Features in Language Models” (2023, arXiv 2309.08600).
- 87 of its 231 mapped papers (38%) cite “Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders” (2024, arXiv 2407.14435).
- 13 new papers 24 Sep–14 Oct.

## Most cited here

- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023), cited by 171 papers here
- [Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders](https://mlsanity.com/paper/2407.14435/) (2024), cited by 87 papers here
- [Scaling and evaluating sparse autoencoders](https://mlsanity.com/paper/2406.04093/) (2024), cited by 82 papers here
- [Improving Dictionary Learning with Gated Sparse Autoencoders](https://mlsanity.com/paper/2404.16014/) (2024), cited by 51 papers here
- [A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders](https://mlsanity.com/paper/2409.14507/) (2024), cited by 46 papers here
- [Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders](https://mlsanity.com/paper/2410.20526/) (2024), cited by 45 papers here
- [SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability](https://mlsanity.com/paper/2503.09532/) (2025), cited by 43 papers here
- [Automatically Interpreting Millions of Features in Large Language Models](https://mlsanity.com/paper/2410.13928/) (2024), cited by 33 papers here
- [AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders](https://mlsanity.com/paper/2501.17148/) (2025), cited by 27 papers here
- [Applying sparse autoencoders to unlearn knowledge in language models](https://mlsanity.com/paper/2410.19278/) (2024), cited by 21 papers here

## New (24 Sep–14 Oct)

- [Diminishing Returns of Data in Sparse Autoencoders: Functional Behavior does not Guarantee Feature Reproducibility](https://mlsanity.com/paper/2610.20680/) (2026-10-14)
- [Sparse Autoencoders for Mechanistic Interpretability in NLP: A Critical Survey of Recoverability, Interpretability, and Utility](https://mlsanity.com/paper/2610.20139/) (2026-10-14)
- [Sparse Autoencoders Are a Shared Coordinate System for Symbolic Matching](https://mlsanity.com/paper/2610.19636/) (2026-10-14)
- [Evaluating the Causal Faithfulness of SHAP as a Candidate Attribution Method for SAE Features](https://mlsanity.com/paper/2610.17898/) (2026-10-13)
- [Disentangling Linguistic and Paralinguistic Information with Routed Sparse Autoencoders](https://mlsanity.com/paper/2610.10865/) (2026-10-07)
- [A Testable Theory of Atomic Features](https://mlsanity.com/paper/2610.05794/) (2026-10-05)
- [Active Budget Can Kill Sensitivity: Diagnosing and Repairing TopK Sparse Autoencoder Reliability](https://mlsanity.com/paper/2609.37857/) (2026-09-29)
- [When Trees Are Not Enough: Learning Mixed-Topology Feature Graphs with Adaptive Graph Sparse Autoencoders](https://mlsanity.com/paper/2609.36294/) (2026-09-28)
- [Beyond Token Scale: Chunk-Level Sparse Autoencoders for Reliable Semantic Feature Discovery](https://mlsanity.com/paper/2609.35521/) (2026-09-28)
- [From Input to Output: A Flexible Agent for Dual-End Interpretation of Sparse Autoencoder Features](https://mlsanity.com/paper/2609.35367/) (2026-09-28)
- [Routing Without Embeddings: Fast And Interpretable Routing With Regular Expressions](https://mlsanity.com/paper/2609.34326/) (2026-09-28)
- [Gradients for Interventions and Activations for Detection: Targeted Feature Learning in Language Models](https://mlsanity.com/paper/2609.32355/) (2026-09-26)
- [Parts-of-Speech as Emergent Categories in SAE Latent Space](https://mlsanity.com/paper/2609.29362/) (2026-09-24)