© 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. 25920
    Prev
    Next
    INDEX
    Explanations

    parentheses

    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
     protective
    -0.08
    Mang
    -0.08
     nationalist
    -0.07
     gutt
    -0.07
     uniquely
    -0.07
    igh
    -0.07
     heti
    -0.07
     defensive
    -0.07
     nais
    -0.07
     prophyl
    -0.07
    POSITIVE LOGITS
     superar
    0.09
    ılan
    0.08
     бенз
    0.08
     Advice
    0.08
    -tv
    0.08
    ilir
    0.08
     مؤشر
    0.08
     КП
    0.08
     квали
    0.07
     overcame
    0.07
    Activations Density 0.002%

    No Known Activations