© 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. 112571
    Prev
    Next
    INDEX
    Explanations

    ations

    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
     تُ
    -0.08
     در
    -0.07
     مجال
    -0.07
     bucket
    -0.07
     we're
    -0.07
     looking
    -0.07
     Christmas
    -0.07
    عدين
    -0.07
    Bucket
    -0.07
     تقع
    -0.07
    POSITIVE LOGITS
    remarks
    0.09
    Pkg
    0.08
    _VERBOSE
    0.08
     Kao
    0.08
     Verde
    0.08
    iao
    0.08
    PD
    0.08
     Occasion
    0.08
     Descriptor
    0.07
    (Html
    0.07
    Activations Density 0.002%

    No Known Activations