© 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. 20206
    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
    ,the
    -0.10
    -spec
    -0.10
    -types
    -0.10
    -awareness
    -0.09
    ‌ಗೆ
    -0.09
    -directory
    -0.09
    ‌లో
    -0.09
    -temperature
    -0.09
    -energy
    -0.09
    -ում
    -0.09
    POSITIVE LOGITS
     आदि
    0.09
    450
    0.08
    0.08
    ....↵
    0.08
     síndrome
    0.07
    ↵//
    0.07
     Birds
    0.07
     bz
    0.07
     como
    0.07
     ...)
    0.07
    Activations Density 0.000%

    No Known Activations