© 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. 19-RESID-POST-AA
    11. 102754
    Prev
    Next
    INDEX
    Explanations

    linear algebra and matrices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gs
    -0.08
    윤
    -0.08
    ära
    -0.08
    αν
    -0.08
     பல
    -0.08
     luật
    -0.08
    <!--[
    -0.07
     ಹೆಚ್ಚು
    -0.07
    awule
    -0.07
    oprote
    -0.07
    POSITIVE LOGITS
     njegov
    0.09
     njeg
    0.09
     njegova
    0.08
     njegove
    0.08
     негов
    0.08
    esteld
    0.08
     dik
    0.08
     gange
    0.08
     its
    0.08
     {*}
    0.08
    Activations Density 0.004%

    No Known Activations