© 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. 108153
    Prev
    Next
    INDEX
    Explanations

    face shapes

    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
    appearance
    -0.08
    Appearance
    -0.08
     appearances
    -0.07
     Gen
    -0.07
     intelig
    -0.07
    astream
    -0.07
    variance
    -0.07
     informe
    -0.07
    tiles
    -0.07
    );

↵
    -0.07
    POSITIVE LOGITS
     England
    0.08
     brit
    0.08
    _original
    0.08
    英国
    0.07
    /plain
    0.07
    、西
    0.07
    /category
    0.07
     düz
    0.07
     Engl
    0.07
     Kot
    0.07
    Activations Density 0.001%

    No Known Activations