© 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. 19-RESID-POST-AA
    11. 20389
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     홈페이지
    -0.08
     wellness
    -0.08
     교육
    -0.08
     образователь
    -0.08
     Educational
    -0.08
     Education
    -0.08
     utbild
    -0.08
     Wellness
    -0.08
     Educación
    -0.08
     medarbe
    -0.08
    POSITIVE LOGITS
     fossil
    0.25
     petroleum
    0.23
     petróleo
    0.21
     النفط
    0.19
     pétrole
    0.17
     petro
    0.17
     fós
    0.17
     нефт
    0.16
     Foss
    0.16
     fossils
    0.16
    Activations Density 0.014%

    No Known Activations