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. 58537
    Prev
    Next
    INDEX
    Explanations

    message

    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
     handset
    -0.09
     año
    -0.08
     verein
    -0.08
     ans
    -0.08
     direita
    -0.08
     tasas
    -0.08
     textbook
    -0.08
     niiden
    -0.08
     viento
    -0.07
     herstellen
    -0.07
    POSITIVE LOGITS
     veiligheid
    0.09
    _checker
    0.08
     Look
    0.08
    LOOK
    0.08
    ikhail
    0.08
    CMC
    0.07
     зл
    0.07
    /look
    0.07
    זו
    0.07
     detox
    0.07
    Activations Density 0.018%

    No Known Activations