Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 12011
    Prev
    Next
    INDEX
    Explanations

    ..

    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
     atroc
    -0.08
    ussian
    -0.08
     حرکت
    -0.08
     neeg
    -0.08
    鲁
    -0.08
     evaluating
    -0.07
     ضبط
    -0.07
    819
    -0.07
    818
    -0.07
     evaluate
    -0.07
    POSITIVE LOGITS
    $total
    0.08
    -----↵
    0.08
    ------↵↵
    0.08
     rates
    0.08
    -------↵
    0.08
     Rates
    0.07
     Floors
    0.07
    		  ↵
    0.07
    .lon
    0.07
    rol
    0.07
    Activations Density 0.003%

    No Known Activations