© 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. 20784
    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
    空
    -0.09
    -0.08
     空
    -0.08
     wisdom
    -0.08
    .googleapis
    -0.07
     unatt
    -0.07
    �
    -0.07
     Lisp
    -0.07
     candidature
    -0.07
     accumulating
    -0.07
    POSITIVE LOGITS
    培训
    0.16
     તાલ
    0.14
     treinamento
    0.14
     प्रशिक्षण
    0.14
     تدريب
    0.14
     trainen
    0.13
     പരിശീല
    0.13
     التدريب
    0.13
     szkol
    0.13
    (training
    0.13
    Activations Density 0.024%
    No Known Activations