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. 106355
    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
     fabrics
    -0.08
    =?
    -0.08
    nju
    -0.07
     oscill
    -0.07
    Tiger
    -0.07
     fabric
    -0.07
     upro
    -0.07
    OJ
    -0.07
     тканей
    -0.07
     façon
    -0.07
    POSITIVE LOGITS
     breakthrough
    0.08
     फाय
    0.08
    ွန်
    0.07
    grav
    0.07
     WORK
    0.07
     RT
    0.07
    تح
    0.07
     LOCAL
    0.07
     Kathy
    0.07
     Secretary
    0.07
    Activations Density 0.001%

    No Known Activations