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. 111732
    Prev
    Next
    INDEX
    Explanations

    Hearth

    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
     biodiversity
    -0.08
     Biod
    -0.08
     피부
    -0.08
     медицин
    -0.08
     migraine
    -0.07
    lös
    -0.07
     कान
    -0.07
    lösung
    -0.07
     의료
    -0.07
     רפוא
    -0.07
    POSITIVE LOGITS
    🙂
    0.08
    ytale
    0.08
     :)
    0.08
    凯
    0.08
    τώ
    0.08
    animated
    0.08
    赠
    0.08
    sqlite
    0.08
     დახ
    0.07
     surprise
    0.07
    Activations Density 0.004%

    No Known Activations