© 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. 22608
    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
    治理
    -0.08
     upstream
    -0.08
     criticizing
    -0.08
     weth
    -0.08
    盈利
    -0.08
     مجتمع
    -0.08
     quyền
    -0.08
     nozzle
    -0.08
    平台代理
    -0.08
    priced
    -0.08
    POSITIVE LOGITS
     기억
    0.33
     memory
    0.30
     memorize
    0.30
     geheugen
    0.29
     recall
    0.28
     memória
    0.28
     memor
    0.28
     recuerdos
    0.27
     memoria
    0.27
     Memory
    0.27
    Activations Density 0.035%

    No Known Activations