Korznikov, Anton

1. OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features
   2025/09/26 by Korznikov, Anton, Galichin, Andrey, Dontsov, Alexey +3 · 2 citations
   #FOS: Computer and information sciences #Machine Learning (cs.LG)
2. The Rogue Scalpel: Activation Steering Compromises LLM Safety
   2025/09/26 by Korznikov, Anton, Galichin, Andrey, Dontsov, Alexey +3 · 1 citation
   #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)