© 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. 24997
    Prev
    Next
    INDEX
    Explanations

    board games and geometry

    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
    ിലുള്ള
    -0.08
     sugars
    -0.08
     expediente
    -0.07
     apology
    -0.07
     nisu
    -0.07
     illness
    -0.07
     allure
    -0.07
     aneur
    -0.07
    核心
    -0.07
     sek
    -0.07
    POSITIVE LOGITS
    在那里
    0.09
     southwest
    0.09
     entlang
    0.08
     occupying
    0.08
    	elseif
    0.08
     پک
    0.08
     Scandin
    0.08
     spots
    0.08
     Dorm
    0.07
    moz
    0.07
    Activations Density 0.045%

    No Known Activations