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. 60636
    Prev
    Next
    INDEX
    Explanations

    conflict

    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
     Ig
    -0.08
    prent
    -0.08
     milag
    -0.08
     iceberg
    -0.08
     nuru
    -0.07
    icem
    -0.07
     mirac
    -0.07
    izzati
    -0.07
    ميات
    -0.07
     Sisimi
    -0.07
    POSITIVE LOGITS
     compelling
    0.09
     propel
    0.09
     utama
    0.09
    Driven
    0.09
     antagon
    0.09
     driving
    0.08
    Resolver
    0.08
     الرئيسي
    0.08
    elar
    0.08
     restless
    0.08
    Activations Density 0.009%

    No Known Activations