© 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. 54740
    Prev
    Next
    INDEX
    Explanations

    manager

    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
     electric
    -0.08
     nautical
    -0.07
     crossword
    -0.07
    Digits
    -0.07
     brilliant
    -0.07
     venom
    -0.07
    Electric
    -0.07
     électrique
    -0.07
     Electric
    -0.07
    Crypt
    -0.07
    POSITIVE LOGITS
     நிறுவன
    0.09
    .sales
    0.08
     पद
    0.08
    /reg
    0.08
    .reg
    0.08
    .controllers
    0.08
    defines
    0.08
    LIK
    0.08
    checks
    0.08
     Likes
    0.08
    Activations Density 0.020%

    No Known Activations