© 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. 23-RESID-POST-AA
    11. 50179
    Prev
    Next
    INDEX
    Explanations

    Trans

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    سه
    -0.08
     Venez
    -0.08
    სახ
    -0.08
    161
    -0.08
     κό
    -0.07
     να
    -0.07
    ДА
    -0.07
     ډول
    -0.07
     clique
    -0.07
    ءَ
    -0.07
    POSITIVE LOGITS
    figuration
    0.17
    c
    0.16
    mutation
    0.14
    fig
    0.13
    cendo
    0.13
    migration
    0.13
    mut
    0.13
    figure
    0.13
    FIX
    0.12
    figur
    0.12
    Activations Density 0.003%

    No Known Activations