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. 43317
    Prev
    Next
    INDEX
    Explanations

    international development and policy

    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
     ẹgbẹ
    -0.08
     cercana
    -0.08
    ری
    -0.08
    패
    -0.08
     Sho
    -0.07
     nonsense
    -0.07
     Stir
    -0.07
     talde
    -0.07
    Sho
    -0.07
     неч
    -0.07
    POSITIVE LOGITS
     ప్రభుత్వం
    0.09
     bureaucracy
    0.09
    改善
    0.09
    政府
    0.09
     citizens
    0.09
     forbed
    0.09
     GDP
    0.09
     officially
    0.09
     Improve
    0.09
     improve
    0.09
    Activations Density 0.048%

    No Known Activations