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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110395
    Prev
    Next
    INDEX
    Explanations

    statistics

    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
     squeezed
    -0.08
    DU
    -0.08
    buck
    -0.07
     tummy
    -0.07
    cription
    -0.07
    -commerce
    -0.07
    bring
    -0.07
     tweak
    -0.07
     stuff
    -0.07
     timing
    -0.07
    POSITIVE LOGITS
     sebanyak
    0.09
     участников
    0.09
     আক্রান্ত
    0.08
     Ebenso
    0.08
     Aer
    0.08
    pathy
    0.08
     السكان
    0.08
     المجموعة
    0.08
     пациентов
    0.08
     экземпля
    0.08
    Activations Density 0.015%

    No Known Activations