© 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. 64772
    Prev
    Next
    INDEX
    Explanations

    tf

    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
    ailed
    -0.08
     demise
    -0.07
     AES
    -0.07
     המקומ
    -0.07
     filled
    -0.07
     tall
    -0.07
     fy
    -0.07
     professions
    -0.07
     incapac
    -0.07
     reichen
    -0.07
    POSITIVE LOGITS
    koop
    0.07
    blas
    0.07
    atang
    0.07
     Highway
    0.07
     oats
    0.07
    teborg
    0.07
    rolling
    0.07
    smooth
    0.07
    jej
    0.07
    enever
    0.07
    Activations Density 0.001%

    No Known Activations