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. 585
    Prev
    Next
    INDEX
    Explanations

    trick-or-treating

    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
    弗
    -0.08
    /student
    -0.07
     trock
    -0.07
    -sing
    -0.07
    ণ্ড
    -0.07
     embar
    -0.07
     umfass
    -0.07
     endorsements
    -0.07
     FER
    -0.07
     student's
    -0.07
    POSITIVE LOGITS
    ாய
    0.09
    archy
    0.09
    城区
    0.08
    ाचार
    0.07
     evitare
    0.07
     prestación
    0.07
     Mocht
    0.07
    0.07
     версии
    0.07
     चेत
    0.07
    Activations Density 0.001%

    No Known Activations