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. 60885
    Prev
    Next
    INDEX
    Explanations

    dog

    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
     prestación
    -0.09
     تخص
    -0.08
     внед
    -0.08
     België
    -0.08
     Verenigde
    -0.08
    odata
    -0.08
     ishte
    -0.08
    (Bit
    -0.08
     ప్రచ
    -0.08
     childbirth
    -0.08
    POSITIVE LOGITS
    pee
    0.08
     researcher
    0.07
    413
    0.07
    creased
    0.07
     amoureux
    0.07
     auteurs
    0.07
    -centered
    0.07
    /f
    0.07
     investigadores
    0.07
    rolling
    0.07
    Activations Density 0.003%

    No Known Activations