© 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. 45286
    Prev
    Next
    INDEX
    Explanations

    2

    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
    49
    -0.08
    136
    -0.08
    -bottom
    -0.07
     buzz
    -0.07
    erdem
    -0.07
     sash
    -0.07
    无法
    -0.07
     inspiración
    -0.07
    _TMP
    -0.07
    TOP
    -0.07
    POSITIVE LOGITS
     domen
    0.08
    folder
    0.08
    жение
    0.08
    டுத்து
    0.07
     Weinstein
    0.07
    ಡು
    0.07
     Assim
    0.07
    стер
    0.07
    iddwa
    0.07
     worksheets
    0.07
    Activations Density 0.078%

    No Known Activations