© 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. 21170
    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
     ಅತ್ಯ
    -0.10
     Zukunft
    -0.09
     výsled
    -0.09
     Future
    -0.09
    未来
    -0.09
     efficacement
    -0.08
     ವಿವರ
    -0.08
    _TREE
    -0.08
    成果
    -0.08
    ilas
    -0.08
    POSITIVE LOGITS
     rhwng
    0.14
    među
    0.14
     bejn
    0.14
     between
    0.13
     millum
    0.13
     commas
    0.13
     laarin
    0.13
     между
    0.13
     байни
    0.13
     mellan
    0.12
    Activations Density 0.002%

    No Known Activations