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. 111789
    Prev
    Next
    INDEX
    Explanations

    sulfate

    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
     yields
    -0.08
    ikhail
    -0.07
    仕
    -0.07
     eindeutig
    -0.07
     Kijk
    -0.07
     Kontext
    -0.07
    本
    -0.07
    iras
    -0.07
     railway
    -0.07
     本
    -0.07
    POSITIVE LOGITS
     hacker
    0.09
    uawei
    0.08
    '</
    0.08
     එ
    0.08
     Structured
    0.08
    $core
    0.08
     olyan
    0.08
     neurosc
    0.08
     unpopular
    0.08
     spyware
    0.08
    Activations Density 0.003%

    No Known Activations