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. 11760
    Prev
    Next
    INDEX
    Explanations

    Questions

    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
    Negoti
    -0.08
     negoti
    -0.08
     negotiated
    -0.08
     прогул
    -0.08
    Angel
    -0.07
     Tic
    -0.07
    Opts
    -0.07
     negotiations
    -0.07
    Telefon
    -0.07
    Transparency
    -0.07
    POSITIVE LOGITS
     समी
    0.09
     ბოლო
    0.09
    ؤال
    0.09
     акыр
    0.09
     վերջին
    0.09
     સંબંધ
    0.08
    関連記事
    0.08
    超碰
    0.08
     शीर्ष
    0.08
     ov
    0.08
    Activations Density 0.004%

    No Known Activations