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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 31390
    Prev
    Next
    INDEX
    Explanations

    Lange

    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
     hü
    -0.08
    垃圾
    -0.07
     eas
    -0.07
     பார
    -0.07
    整个
    -0.07
     Navy
    -0.07
    BRA
    -0.07
    infos
    -0.07
     Spitz
    -0.07
    闻
    -0.07
    POSITIVE LOGITS
     plurality
    0.09
     plural
    0.08
     Hare
    0.08
    률
    0.08
     Vas
    0.07
     hospitalization
    0.07
     estudi
    0.07
     detailing
    0.07
     مشتر
    0.07
     functioning
    0.07
    Activations Density 0.000%

    No Known Activations