© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78828
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
     autofocus
    -0.09
    Գ
    -0.09
    定位
    -0.08
    usform
    -0.08
    formas
    -0.08
    Lesson
    -0.08
     Converted
    -0.08
    δα
    -0.08
     Գր
    -0.08
    Tutorial
    -0.08
    POSITIVE LOGITS
     extreme
    0.09
    Extreme
    0.09
    arkt
    0.08
     extrem
    0.08
     Extreme
    0.08
    apon
    0.08
    -ext
    0.08
     zul
    0.07
     cet
    0.07
     latex
    0.07
    Activations Density 0.002%

    No Known Activations