© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 31072
    Prev
    Next
    INDEX
    Explanations

    math puzzles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �览
    -0.08
     mitigation
    -0.08
     Tijdens
    -0.08
     selama
    -0.08
     podczas
    -0.08
     během
    -0.08
     ಸೇರಿದಂತೆ
    -0.08
     դատ
    -0.08
     risking
    -0.08
    during
    -0.08
    POSITIVE LOGITS
    谜
    0.09
     ISBN
    0.09
     indexing
    0.09
     solved
    0.08
     Fibonacci
    0.08
    Palindrome
    0.08
    Somos
    0.08
     maps
    0.08
     Número
    0.08
     vivos
    0.08
    Activations Density 0.035%

    No Known Activations