© 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. 19-RESID-POST-AA
    11. 18364
    Prev
    Next
    INDEX
    Explanations

    GIS

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (schedule
    -0.09
     Baldwin
    -0.09
    طور
    -0.09
     SUBSTITUTE
    -0.08
     orderly
    -0.08
     submiss
    -0.08
    賞
    -0.08
    فن
    -0.08
    انہ
    -0.08
    (noun
    -0.08
    POSITIVE LOGITS
     raster
    0.10
     слой
    0.10
     GIS
    0.10
    GIS
    0.09
    ospatial
    0.09
     leaflet
    0.09
     слоя
    0.09
    ecode
    0.09
    Services
    0.09
    odata
    0.09
    Activations Density 0.006%

    No Known Activations