© 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. 63306
    Prev
    Next
    INDEX
    Explanations

    sporting events

    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
    .volume
    -0.08
     poprzez
    -0.08
     mande
    -0.08
     flamb
    -0.07
     mentor
    -0.07
    indice
    -0.07
    >]
    -0.07
     পুর
    -0.07
     положения
    -0.07
    317
    -0.07
    POSITIVE LOGITS
    chny
    0.08
     blieb
    0.08
    าว
    0.08
     hech
    0.08
     dominated
    0.08
     vegetar
    0.08
    dfs
    0.08
     gedurende
    0.07
     unchanged
    0.07
     Colon
    0.07
    Activations Density 0.037%

    No Known Activations