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. 77194
    Prev
    Next
    INDEX
    Explanations

    relative

    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
     Successfully
    -0.09
    boat
    -0.09
     humility
    -0.08
    azine
    -0.08
    /**/*.
    -0.08
    stered
    -0.08
     bedside
    -0.08
     compassionate
    -0.08
    Beauty
    -0.07
     courage
    -0.07
    POSITIVE LOGITS
    以及
    0.10
    是否
    0.10
     وكيف
    0.09
     relation
    0.09
    有没有
    0.09
     zda
    0.08
    哪些
    0.08
     wzglę
    0.08
     cuándo
    0.08
     是否
    0.08
    Activations Density 0.056%

    No Known Activations