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. 60867
    Prev
    Next
    INDEX
    Explanations

    alarm

    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
     Willow
    -0.07
     ઇ
    -0.07
    arske
    -0.07
    .consumer
    -0.07
    endor
    -0.07
    -0.07
     constraint
    -0.07
    ಿಲ್ಲ
    -0.07
     ряд
    -0.06
    <|reserved_200016|>
    -0.06
    POSITIVE LOGITS
     cliquez
    0.09
    meeting
    0.08
     clic
    0.08
     උප
    0.08
     réunion
    0.08
    ระ
    0.08
    resar
    0.08
     Oll
    0.07
    _cls
    0.07
     genuine
    0.07
    Activations Density 0.001%

    No Known Activations