Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8342
    Prev
    Next
    INDEX
    Explanations

    traditional

    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
     Roberts
    -0.08
    ıda
    -0.08
     Bis
    -0.08
     Dijon
    -0.08
     Quart
    -0.08
    Extras
    -0.07
     coats
    -0.07
    Lip
    -0.07
     обе
    -0.07
     toutes
    -0.07
    POSITIVE LOGITS
    -fashioned
    0.10
     التقلي
    0.09
     traditional
    0.09
    传统
    0.08
    traditional
    0.08
     tradicional
    0.08
     wisdom
    0.08
    ��
    0.08
     Rory
    0.08
     taught
    0.08
    Activations Density 0.021%

    No Known Activations