© 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 EvalsExportsAPI 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. 20674
    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
     trasfer
    -0.08
     تعديل
    -0.08
    avyo
    -0.08
     insufficient
    -0.08
    .retrieve
    -0.07
    .cleanup
    -0.07
     retrans
    -0.07
     ಕೆಲವು
    -0.07
     дополнительных
    -0.07
     excluir
    -0.07
    POSITIVE LOGITS
     mindset
    0.29
     mentality
    0.28
    意识
    0.25
     consciousness
    0.23
     awareness
    0.23
     ethos
    0.22
    -minded
    0.21
    -awareness
    0.21
     minded
    0.20
     instincts
    0.20
    Activations Density 0.098%

    No Known Activations