© 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. 64460
    Prev
    Next
    INDEX
    Explanations

    -

    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
    ítés
    -0.08
     brushes
    -0.07
     occupational
    -0.07
    ಜೆ
    -0.07
    -0.07
     irregular
    -0.07
     conce
    -0.07
     override
    -0.07
     Dimension
    -0.07
    ಮ
    -0.07
    POSITIVE LOGITS
    cpy
    0.08
     செய
    0.08
     thy
    0.08
     �
    0.08
     曾
    0.08
     بعيد
    0.08
     CMD
    0.08
    μαστε
    0.07
     pů
    0.07
    eerd
    0.07
    Activations Density 0.013%
    No Known Activations