© 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. 23-RESID-POST-AA
    11. 50532
    Prev
    Next
    INDEX
    Explanations

    maintenance

    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
     આરોપ
    -0.08
     abbreviation
    -0.07
     Clickfunnels
    -0.07
    .Compiler
    -0.07
    ોળ
    -0.07
     Gewinner
    -0.07
     bryst
    -0.07
     Zoom
    -0.07
     कहानी
    -0.07
     onion
    -0.07
    POSITIVE LOGITS
     maintenance
    0.56
     Maintenance
    0.53
    Maintenance
    0.53
     mantenimiento
    0.51
    maintenance
    0.50
    维护
    0.50
     manutenção
    0.49
     onderhoud
    0.47
     유지
    0.43
    -maint
    0.42
    Activations Density 0.137%

    No Known Activations