© 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. 19252
    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
     slight
    -0.10
     некоторое
    -0.10
    199
    -0.09
    -0.09
     מעט
    -0.09
     modest
    -0.09
    rogen
    -0.09
     somewhat
    -0.09
    150
    -0.09
    ５０
    -0.09
    POSITIVE LOGITS
     overview
    0.11
     rápida
    0.10
    快速
    0.10
    씩
    0.10
     snel
    0.10
     vistazo
    0.10
     synopsis
    0.10
     ઝડપી
    0.10
     gyors
    0.10
     kennism
    0.09
    Activations Density 0.018%

    No Known Activations