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. 53014
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
    物
    -0.07
     प्रतिनिध
    -0.07
     물
    -0.07
     rebellious
    -0.07
    ();↵↵
    -0.07
    _repr
    -0.07
     annum
    -0.07
    Physical
    -0.07
    iceps
    -0.07
    Runner
    -0.07
    POSITIVE LOGITS
     POST
    0.08
    Kansas
    0.08
    OFFSET
    0.08
     jotka
    0.08
    ueira
    0.08
    ૂબ
    0.07
     جيڪي
    0.07
     berücksicht
    0.07
     lähe
    0.07
     Karnataka
    0.07
    Activations Density 0.017%

    No Known Activations