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. 53126
    Prev
    Next
    INDEX
    Explanations

    themes

    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
     param
    -0.09
    param
    -0.08
     demons
    -0.08
    اده
    -0.07
    Param
    -0.07
    aktif
    -0.07
    	param
    -0.07
     demon
    -0.07
    ();
    -0.07
    oric
    -0.07
    POSITIVE LOGITS
    纲
    0.09
    涵
    0.09
    选四
    0.09
     headings
    0.09
     أربع
    0.09
     מתוך
    0.08
    热点
    0.08
    观点
    0.08
    หัว
    0.08
    精选
    0.08
    Activations Density 0.010%

    No Known Activations