© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 64179
    Prev
    Next
    INDEX
    Explanations

    ТО

    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
    criminal
    -0.08
     ((__
    -0.08
     offenses
    -0.08
     amat
    -0.08
     plaintiffs
    -0.07
     homicide
    -0.07
     व्यापक
    -0.07
     crime
    -0.07
     त्र
    -0.07
     defendants
    -0.07
    POSITIVE LOGITS
    osp
    0.09
    ្ល
    0.08
    hoof
    0.08
    Nut
    0.08
    umbotron
    0.08
     motivating
    0.08
    jado
    0.08
    rong
    0.07
    ANDROID
    0.07
    .non
    0.07
    Activations Density 0.002%

    No Known Activations