© 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. 3-RESID-POST-AA
    11. 1239
    Prev
    Next
    INDEX
    Explanations

    Synchronization and connection software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     toán
    -0.08
     ع
    -0.08
     hurdle
    -0.08
     cutter
    -0.07
     المحكمة
    -0.07
     والف
    -0.07
     Bek
    -0.07
     болг
    -0.07
     конферен
    -0.07
     Membership
    -0.07
    POSITIVE LOGITS
    ుఖ
    0.08
    ilia
    0.07
     provocado
    0.07
     Joi
    0.07
     చేర
    0.07
     заним
    0.07
     ew
    0.07
    trusted
    0.07
     transformations
    0.07
    &quot
    0.07
    Activations Density 0.000%

    No Known Activations