© 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. 21142
    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
    .INTERNAL
    -0.08
     birbir
    -0.08
    -
    -0.08
    -events
    -0.08
    -output
    -0.08
    -h
    -0.07
    -components
    -0.07
    %
    -0.07
    -event
    -0.07
    -component
    -0.07
    POSITIVE LOGITS
     with
    0.17
     avec
    0.16
     עם
    0.16
     pẹlu
    0.16
     với
    0.16
    	with
    0.15
    กับ
    0.15
     nrog
    0.14
     dengan
    0.14
     Avec
    0.14
    Activations Density 0.025%

    No Known Activations