© 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. 114322
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     Pied
    -0.08
    hamb
    -0.07
    gart
    -0.07
    akeup
    -0.07
     Vér
    -0.07
     Hội
    -0.07
    hara
    -0.07
     akan
    -0.07
     Vish
    -0.07
    imo
    -0.07
    POSITIVE LOGITS
    .instant
    0.08
     natür
    0.08
    bearing
    0.08
     parcela
    0.08
     trate
    0.08
     Proced
    0.08
     proced
    0.07
    ochem
    0.07
    γμα
    0.07
     socialista
    0.07
    Activations Density 0.070%

    No Known Activations