Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 55546
    Prev
    Next
    INDEX
    Explanations

    write

    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
     yder
    -0.09
    oloji
    -0.08
     αυ
    -0.08
     oqo
    -0.08
     употреб
    -0.08
     dünya
    -0.08
     Россия
    -0.08
     otten
    -0.08
    iaires
    -0.08
     Wereld
    -0.08
    POSITIVE LOGITS
    /render
    0.09
     bestseller
    0.08
    那些
    0.08
    一本
    0.08
     constraint
    0.08
     guaranteeing
    0.07
     المزيد
    0.07
    退休
    0.07
    ∀
    0.07
     masterpiece
    0.07
    Activations Density 0.033%

    No Known Activations