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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12891
    Prev
    Next
    INDEX
    Explanations

    period

    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
    (scale
    -0.08
    Pipe
    -0.08
    [x
    -0.07
    ПК
    -0.07
     kill
    -0.07
    (pipe
    -0.07
    [B
    -0.07
     అ
    -0.07
     περι
    -0.07
    anno
    -0.07
    POSITIVE LOGITS
     Emerson
    0.08
     accompaniment
    0.08
     ry
    0.07
    enes
    0.07
     Saya
    0.07
     Must
    0.07
    redict
    0.07
     John
    0.07
     women's
    0.07
    kor
    0.07
    Activations Density 0.013%

    No Known Activations