© 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. 44747
    Prev
    Next
    INDEX
    Explanations

    General knowledge

    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
     begged
    -0.07
    -0.07
     rese
    -0.07
     the
    -0.07
     uchun
    -0.07
     of
    -0.07
     için
    -0.07
     dann
    -0.07
    艾
    -0.07
     proceeds
    -0.07
    POSITIVE LOGITS
    ことで
    0.10
     enables
    0.09
     통해
    0.09
     ermöglicht
    0.09
     avulla
    0.09
     totiž
    0.09
     Enables
    0.09
     infatti
    0.09
     média
    0.09
     фундамент
    0.08
    Activations Density 0.261%
    No Known Activations