© 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. 19454
    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
     ».↵↵
    -0.09
     effectiveness
    -0.08
    :type
    -0.07
    ".↵↵
    -0.07
    rebbe
    -0.07
     code
    -0.07
     möglicherweise
    -0.07
     correctness
    -0.07
    resse
    -0.07
     data
    -0.07
    POSITIVE LOGITS
    ，《
    0.09
     ועוד
    0.09
    ,香港
    0.09
     eighteen
    0.09
     twelve
    0.09
    oju
    0.08
    !!↵
    0.08
    Hot
    0.08
    ，中国
    0.08
     Chinatown
    0.08
    Activations Density 0.092%

    No Known Activations