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. 11901
    Prev
    Next
    INDEX
    Explanations

    repel

    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
    gleichen
    -0.08
     steam
    -0.07
     Opera
    -0.07
    指出
    -0.07
    -0.07
    Clock
    -0.07
     Pie
    -0.07
    Pero
    -0.07
    ercise
    -0.07
     satisfaire
    -0.07
    POSITIVE LOGITS
    itwa
    0.08
    -enh
    0.08
    achadh
    0.08
     avocat
    0.08
    �
    0.08
    avn
    0.08
     към
    0.07
     recipes
    0.07
     قات
    0.07
    ופו
    0.07
    Activations Density 0.002%

    No Known Activations