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. 55905
    Prev
    Next
    INDEX
    Explanations

    window

    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
     derivatives
    -0.08
     Poly
    -0.07
    Append
    -0.07
     appendix
    -0.07
    hardt
    -0.07
     poly
    -0.07
     Appendix
    -0.07
    Incorrect
    -0.07
     derivative
    -0.07
    poly
    -0.07
    POSITIVE LOGITS
     তাক
    0.09
     ноч
    0.09
     तेज
    0.09
     seasonal
    0.09
     Свет
    0.09
     renk
    0.09
     daylight
    0.09
     రంగ
    0.09
     φω
    0.08
     Brighton
    0.08
    Activations Density 0.003%

    No Known Activations