© 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. 113615
    Prev
    Next
    INDEX
    Explanations

    title

    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
     اق
    -0.08
     tier
    -0.08
     targeted
    -0.08
     hier
    -0.08
     catal
    -0.07
     projected
    -0.07
     el
    -0.07
    Projected
    -0.07
    Catal
    -0.07
    unod
    -0.07
    POSITIVE LOGITS
    >.</
    0.09
     검사
    0.09
     Prüfung
    0.08
    >Error
    0.08
     perfe
    0.08
    >Password
    0.08
    /^
    0.08
     Examination
    0.08
     cleansing
    0.08
     komplik
    0.08
    Activations Density 0.002%

    No Known Activations