Scholar
Anton Korznikov
Google Scholar ID: PiY7hf4AAAAJ
Independent researcher
mechanistic interpretability
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
0
H-index
0
i10-index
0
Publications
2
Co-authors
0
Publications
5 items
Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs
2026
Cited
0
What Attention Recalls and Recurrence Controls in Hybrid Language Models
2026
Cited
0
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?
2026
Cited
0
The Rogue Scalpel: Activation Steering Compromises LLM Safety
2025
Cited
0
OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features
2025
Cited
0
