© 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. 21356
    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
    other
    -0.09
     anderes
    -0.08
    -W
    -0.08
    ful
    -0.08
    ають
    -0.08
     приятно
    -0.08
     अच्छी
    -0.08
    ा
    -0.08
     improve
    -0.08
    बे
    -0.08
    POSITIVE LOGITS
     ज्ञान
    0.09
     enough
    0.09
     ਗਿਆ
    0.09
     uttry
    0.09
     പങ്ക
    0.08
     أعلن
    0.08
     denunciar
    0.08
     proceeding
    0.08
     denúncia
    0.08
    _request
    0.08
    Activations Density 0.004%

    No Known Activations