© 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. 21377
    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
     nzira
    -0.08
    策略
    -0.08
    akses
    -0.08
     viscos
    -0.08
     bases
    -0.08
     eriş
    -0.08
     işe
    -0.08
     ücret
    -0.08
     interfaces
    -0.08
     uburyo
    -0.07
    POSITIVE LOGITS
     gebeurtenissen
    0.38
     Ereign
    0.35
     events
    0.35
     événements
    0.34
     события
    0.34
     acontecimentos
    0.34
     الأحداث
    0.34
     eventos
    0.33
     wydar
    0.33
     사건
    0.32
    Activations Density 0.060%

    No Known Activations