© 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. 7-RESID-POST-AA
    11. 942
    Prev
    Next
    INDEX
    Explanations

    ;

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     libert
    -0.08
    BEL
    -0.07
     east
    -0.07
    ومت
    -0.07
     bachelors
    -0.07
    -East
    -0.07
     nomin
    -0.07
     सां
    -0.07
    Ho
    -0.07
    orc
    -0.07
    POSITIVE LOGITS
    ги
    0.08
    shed
    0.08
    냐
    0.08
    ার
    0.08
    hesia
    0.08
     entscheid
    0.08
     অন্যতম
    0.07
     fő
    0.07
     biodegradable
    0.07
     injunction
    0.07
    Activations Density 0.001%

    No Known Activations