© 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 EvalsExportsinterp-engineNEWAPI 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. 22246
    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
     voyeur
    -0.10
     autobi
    -0.09
     selfie
    -0.09
    青春
    -0.09
    自慰
    -0.08
     Circus
    -0.08
     γρά
    -0.08
     ciya
    -0.08
    .Navigation
    -0.08
    考试
    -0.08
    POSITIVE LOGITS
     suppliers
    0.36
     leveranciers
    0.33
     supplier
    0.33
     fornecedores
    0.33
    采购
    0.32
     Suppliers
    0.32
     fournisseurs
    0.30
     Supplier
    0.30
    Supplier
    0.29
    supplier
    0.29
    Activations Density 0.057%

    No Known Activations