© 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. 44543
    Prev
    Next
    INDEX
    Explanations

    whisk

    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
    လုပ်
    -0.09
     confronted
    -0.08
     помещении
    -0.08
    energ
    -0.08
     MATRIX
    -0.08
     laboratoire
    -0.08
     energ
    -0.08
     manpower
    -0.08
     loi
    -0.08
     supr
    -0.07
    POSITIVE LOGITS
    纹
    0.09
    bullet
    0.09
    ുള്ള
    0.08
    刺
    0.08
     Sharp
    0.08
     ve
    0.07
    otechnology
    0.07
    Width
    0.07
     eyelashes
    0.07
    Bullet
    0.07
    Activations Density 0.001%

    No Known Activations