© 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. 21782
    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
     agua
    -0.10
    amo
    -0.09
     पानी
    -0.08
     motives
    -0.08
     vody
    -0.08
     acqua
    -0.07
    .crypto
    -0.07
     хранения
    -0.07
     воды
    -0.07
     polymer
    -0.07
    POSITIVE LOGITS
     পুরো
    0.14
     పూర్తి
    0.12
     全
    0.12
     સંપૂર્ણ
    0.12
     పూర్త
    0.11
     full
    0.11
     FULL
    0.11
     முழ
    0.11
     മുഴ
    0.11
     പൂര്
    0.10
    Activations Density 0.003%

    No Known Activations