© 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. 3-RESID-POST-AA
    11. 1183
    Prev
    Next
    INDEX
    Explanations

    America

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hyst
    -0.08
     archa
    -0.08
    czas
    -0.07
     ಸಮ
    -0.07
    arca
    -0.07
     structural
    -0.07
    弱
    -0.07
     multim
    -0.07
    lsen
    -0.07
     Protocol
    -0.07
    POSITIVE LOGITS
     evangel
    0.09
     nanot
    0.08
    (radius
    0.08
     evade
    0.08
    (rad
    0.08
     cient
    0.08
     radion
    0.08
    救
    0.08
     enthr
    0.08
    фика
    0.07
    Activations Density 0.059%

    No Known Activations