© 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. 21001
    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
    的
    -0.09
    umption
    -0.09
     जिस
    -0.09
     lorsqu
    -0.08
    开彩
    -0.08
     wanneer
    -0.08
     lorsque
    -0.08
    ვას
    -0.08
     lesqu
    -0.08
     maturation
    -0.07
    POSITIVE LOGITS
    Sim
    0.09
    También
    0.09
    Assignments
    0.08
    "));↵
    0.08
    Also
    0.08
    steps
    0.08
    "});↵
    0.08
    Không
    0.08
    Também
    0.08
    Lets
    0.08
    Activations Density 0.000%

    No Known Activations