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. 53854
    Prev
    Next
    INDEX
    Explanations

    Forgetting something

    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
     мир
    -0.09
     Psal
    -0.09
    :#
    -0.08
     والغ
    -0.08
     допом
    -0.08
     Satur
    -0.08
     literary
    -0.08
     Shui
    -0.08
    testen
    -0.08
     Cui
    -0.08
    POSITIVE LOGITS
     check
    0.08
     terribly
    0.08
    遗漏
    0.08
     forgot
    0.08
     habitual
    0.08
     habits
    0.07
    check
    0.07
     omissions
    0.07
    Check
    0.07
     missing
    0.07
    Activations Density 0.021%

    No Known Activations