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. 43378
    Prev
    Next
    INDEX
    Explanations

    Napoleon's exile

    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
     jazz
    -0.09
     synerg
    -0.08
     metal
    -0.08
     металл
    -0.07
     mic
    -0.07
    ラス
    -0.07
     mű
    -0.07
     sax
    -0.07
    रस
    -0.07
    idy
    -0.07
    POSITIVE LOGITS
     benutzen
    0.08
     sead
    0.08
    _problem
    0.07
     defects
    0.07
    ੱਖ
    0.07
     समस्य
    0.07
     benutzt
    0.07
     상세
    0.07
     Hof
    0.07
     poissons
    0.07
    Activations Density 0.002%

    No Known Activations