© 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. 19948
    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
    197
    -0.09
     strcmp
    -0.09
     Larry
    -0.09
     انھ
    -0.09
    'année
    -0.08
    	scanf
    -0.08
     acknow
    -0.08
    	strcat
    -0.08
    	strcpy
    -0.08
    strlen
    -0.08
    POSITIVE LOGITS
    (Path
    0.13
     pathlib
    0.12
    <Path
    0.11
    .relative
    0.11
    .resolve
    0.10
    .mkdir
    0.10
    .Files
    0.10
    .unlink
    0.10
     Path
    0.09
    .tom
    0.09
    Activations Density 0.005%

    No Known Activations