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. 15-RESID-POST-AA
    6. 19269
    Prev
    Next
    INDEX
    Explanations

    Express

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    рина
    -0.08
     trạng
    -0.08
     linguistic
    -0.08
     الظروف
    -0.08
     ),↵↵
    -0.08
    ുവര
    -0.08
    żu
    -0.08
     hemel
    -0.08
     choir
    -0.08
     заход
    -0.08
    POSITIVE LOGITS
     وبعض
    0.09
    .js
    0.08
    .Builder
    0.08
    ,用
    0.08
    -fer
    0.08
    JS
    0.08
     kurul
    0.08
    -based
    0.08
     outf
    0.08
     ಬಳ
    0.08
    Activations Density 0.010%

    No Known Activations