© 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. 19-RESID-POST-AA
    11. 103279
    Prev
    Next
    INDEX
    Explanations

    say UI/Front-end

    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
    )↵
    -0.12
    :↵
    -0.11
    :
    -0.11
    )↵↵
    -0.10
    :↵↵
    -0.10
    ↵
    -0.09
     that
    -0.09
    ,
    -0.09
    (in
    -0.09
    :)↵
    -0.08
    POSITIVE LOGITS
    �
    0.11
    **)
    0.11
    �
    0.11
    ១
    0.10
    �
    0.10
    8
    0.10
    ០
    0.09
    oltre
    0.09
    16
    0.09
    เม
    0.09
    Activations Density 0.004%

    No Known Activations