© 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. 68197
    Prev
    Next
    INDEX
    Explanations

    ank

    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
     absentee
    -0.08
     Precis
    -0.08
     disabilities
    -0.08
     Suzuki
    -0.08
     cotid
    -0.07
    Spectrum
    -0.07
     principally
    -0.07
     diagnosed
    -0.07
     ക്ഷ
    -0.07
     pinpoint
    -0.07
    POSITIVE LOGITS
     буде
    0.08
     будет
    0.08
     verd
    0.08
    यो
    0.08
     Miley
    0.08
     mud
    0.08
    ита
    0.07
     यो
    0.07
     Vince
    0.07
     imb
    0.07
    Activations Density 0.000%

    No Known Activations