© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 114326
    Prev
    Next
    INDEX
    Explanations

    questions and uncertainty

    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
     востреб
    -0.07
    ાવતા
    -0.07
    oss
    -0.07
     muun
    -0.07
    踪
    -0.07
     наличие
    -0.07
     themed
    -0.07
    eday
    -0.07
    姿
    -0.07
     이상의
    -0.07
    POSITIVE LOGITS
     coupons
    0.09
    эконом
    0.08
     disregard
    0.08
     unabh
    0.08
     ignores
    0.08
     шару
    0.08
     independiente
    0.08
     indépend
    0.08
     independientes
    0.07
     faire
    0.07
    Activations Density 0.066%

    No Known Activations