© 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. 99465
    Prev
    Next
    INDEX
    Explanations

    Chatbot completions

    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
    DDD
    -0.09
    utho
    -0.07
    innie
    -0.07
    ifting
    -0.07
    Observ
    -0.07
    ifu
    -0.07
    ió
    -0.07
    ,h
    -0.07
    /apache
    -0.07
    -src
    -0.07
    POSITIVE LOGITS
    จำ
    0.08
     endlich
    0.07
     тұр
    0.07
     acerc
    0.07
     espal
    0.07
     factorial
    0.07
     sementes
    0.07
     orthodox
    0.07
     ersta
    0.07
     تە
    0.07
    Activations Density 0.014%

    No Known Activations