OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features Paper • 2509.22033 • Published Sep 26, 2025 • 19
The Rogue Scalpel: Activation Steering Compromises LLM Safety Paper • 2509.22067 • Published Sep 26, 2025 • 28
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders Paper • 2503.18878 • Published Mar 24, 2025 • 119
SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators Paper • 2502.06394 • Published Feb 10, 2025 • 89
