William Saunders

Identifiers

• name variant William Saunders 0.60 · backfill

Papers (8)

1. Emotion Concepts and their Function in a Large Language Model cs.AI · 2026 · author #3
2. Open Problems in Mechanistic Interpretability cs.LG · 2025 · author #22
3. Self-critiquing models for assisting human evaluators cs.CL · 2022 · author #1
4. Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models cs.CL · 2022 · author #425
5. WebGPT: Browser-assisted question-answering with human feedback cs.CL · 2021 · author #10
6. Evaluating Large Language Models Trained on Code cs.LG · 2021 · author #41
7. Trial without Error: Towards Safe Reinforcement Learning via Human Intervention cs.AI · 2017 · author #1
8. The 6dF Galaxy Survey astro-ph · 2003 · author #5

Mentions

• 2206.05802 #1 · arxiv_oai · confidence 0.70 William Saunders

Frequent Coauthors

• Jeff Wu 3 shared papers
• Alethea Power 2 shared papers
• Alex Ray 2 shared papers
• Christopher Hesse 2 shared papers
• Elizabeth Barnes 2 shared papers
• Girish Sastry 2 shared papers
• Gretchen Krueger 2 shared papers
• Jack Lindsey 2 shared papers
• Jacob Hilton 2 shared papers
• Jan Leike 2 shared papers
• Jared Kaplan 2 shared papers
• Joshua Batson 2 shared papers
• Long Ouyang 2 shared papers
• Matthew Knight 2 shared papers
• Mor Geva 2 shared papers
• Owain Evans 2 shared papers
• Shantanu Jain 2 shared papers
• Stella Biderman 2 shared papers
• Suchir Balaji 2 shared papers
• Vedant Misra 2 shared papers