© 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. 19-RESID-POST-AA
    11. 103453
    Prev
    Next
    INDEX
    Explanations

    Programmatic/Symbolic expressions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ències
    -0.08
     भावना
    -0.08
     ഇവിടെ
    -0.08
     არ
    -0.08
    -0.08
     riguarda
    -0.08
     বলতে
    -0.08
     ഇനി
    -0.08
     repudi
    -0.08
     hano
    -0.08
    POSITIVE LOGITS
    (item
    0.08
    相談
    0.08
    gebild
    0.08
    (image
    0.07
     teamed
    0.07
     item
    0.07
     creen
    0.07
    ுமே
    0.07
    ((((
    0.07
    ंथ
    0.07
    Activations Density 0.000%
    No Known Activations