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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 129115
    Prev
    Next
    INDEX
    Explanations

    Programming, math, and geometry

    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
    (None
    -0.08
    സി
    -0.07
     Nass
    -0.07
     സാമ്പ
    -0.07
     pamilya
    -0.07
    лігі
    -0.07
    -0.07
     семья
    -0.07
     Polk
    -0.07
     પરિવાર
    -0.07
    POSITIVE LOGITS
     equality
    0.09
     reunión
    0.08
    amac
    0.08
     Sheet
    0.07
    牧
    0.07
     Date
    0.07
     invariant
    0.07
     návr
    0.07
     Equality
    0.07
     encontro
    0.07
    Activations Density 0.001%
    No Known Activations