© 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. 95435
    Prev
    Next
    INDEX
    Explanations

    ICD coding

    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
    Dave
    -0.09
     =)↵↵
    -0.08
    Carol
    -0.08
     teammates
    -0.08
    Oo
    -0.08
     peers
    -0.08
    ledge
    -0.08
    Teams
    -0.07
    Oops
    -0.07
     disciplines
    -0.07
    POSITIVE LOGITS
     unspecified
    0.09
     miscellaneous
    0.09
     Misc
    0.08
     specify
    0.08
     prescribe
    0.08
     निर्द
    0.08
     신고
    0.08
    misc
    0.08
    if
    0.08
     conceal
    0.08
    Activations Density 0.004%

    No Known Activations