Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 112262
    Prev
    Next
    INDEX
    Explanations

    C code

    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
     Angeb
    -0.08
    _offer
    -0.08
     genus
    -0.08
    (side
    -0.08
    Offer
    -0.08
    .Prepared
    -0.07
    競
    -0.07
     reizen
    -0.07
    찰
    -0.07
    측
    -0.07
    POSITIVE LOGITS
     caract
    0.09
     характ
    0.08
    直到
    0.08
     caracter
    0.08
     રહ્યા
    0.08
     caratter
    0.08
    字符
    0.08
     consecut
    0.08
     подвер
    0.08
     getchar
    0.08
    Activations Density 0.003%

    No Known Activations