© 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. 63222
    Prev
    Next
    INDEX
    Explanations

    way

    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
     ub
    -0.08
     budding
    -0.08
    vic
    -0.08
     liz
    -0.07
    roduction
    -0.07
     uba
    -0.07
    velo
    -0.07
    usiya
    -0.07
    વાલ
    -0.07
    UBA
    -0.07
    POSITIVE LOGITS
     outweigh
    0.09
     outwe
    0.09
     costo
    0.09
     enough
    0.08
     exceeds
    0.08
     surpassed
    0.07
     discrep
    0.07
     genug
    0.07
     restrictive
    0.07
     सारे
    0.07
    Activations Density 0.013%

    No Known Activations