© 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. 18716
    Prev
    Next
    INDEX
    Explanations

    new

    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
    =?,
    -0.09
    ையான
    -0.08
    -factor
    -0.08
     možda
    -0.08
     variant
    -0.08
     okanye
    -0.08
     häzirki
    -0.08
    velo
    -0.07
     einhver
    -0.07
     შესაძლოა
    -0.07
    POSITIVE LOGITS
     lines
    0.12
     "\
    0.11
    ,"\
    0.11
     líneas
    0.11
     linha
    0.10
    	line
    0.10
     linhas
    0.10
     текста
    0.10
     line
    0.10
     línea
    0.10
    Activations Density 0.001%

    No Known Activations