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. 55995
    Prev
    Next
    INDEX
    Explanations

    applications and forms

    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
     Alaska
    -0.10
    になる
    -0.09
     §
    -0.09
     ニ
    -0.09
     Nevada
    -0.09
    §
    -0.09
     Natalie
    -0.08
    ころ
    -0.08
     opper
    -0.08
    interp
    -0.08
    POSITIVE LOGITS
     Delhi
    0.19
     భారత
    0.19
     Kerala
    0.18
     இந்திய
    0.18
    Delhi
    0.18
     ભારતીય
    0.17
     ભારત
    0.17
     भारतीय
    0.17
     Rajasthan
    0.17
     Mumbai
    0.17
    Activations Density 3.276%

    No Known Activations