© 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. 18556
    Prev
    Next
    INDEX
    Explanations

    tokens contain "op"

    np_max-act-logits · gemini-2.0-flash
    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
     filename
    -0.10
     파일
    -0.10
    Filename
    -0.10
    =file
    -0.10
    .File
    -0.10
    (filename
    -0.09
     File
    -0.09
     файл
    -0.09
    File
    -0.09
    	filename
    -0.09
    POSITIVE LOGITS
     rooftop
    0.25
     balcony
    0.23
     terraza
    0.23
     balkon
    0.21
     balconies
    0.21
     terrace
    0.20
     varanda
    0.20
     Balcony
    0.19
     Balkon
    0.19
     terrasse
    0.18
    Activations Density 0.038%

    No Known Activations