© 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. 21665
    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
    -President
    -0.09
    -jährige
    -0.08
    Helvetica
    -0.08
    >Total
    -0.08
    	Last
    -0.08
    .Total
    -0.08
    Nome
    -0.08
    -Day
    -0.08
    _Total
    -0.08
    -Year
    -0.08
    POSITIVE LOGITS
     utils
    0.21
    _utils
    0.19
    utils
    0.19
    /utils
    0.18
    .utils
    0.18
    	utils
    0.17
     utilities
    0.16
     Utils
    0.15
    Utils
    0.15
     util
    0.14
    Activations Density 0.008%

    No Known Activations