© 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. 11-RESID-POST-AA
    11. 111078
    Prev
    Next
    INDEX
    Explanations

    work-life balance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Friedrich
    -0.07
    candidate
    -0.07
     atlas
    -0.07
    adena
    -0.07
    að
    -0.07
    .BAD
    -0.07
    EC
    -0.07
     candidate
    -0.07
    .-
    -0.07
     Schwarz
    -0.07
    POSITIVE LOGITS
     weekends
    0.09
     evenings
    0.08
     国内
    0.08
     weekdays
    0.08
    不得
    0.08
     produtividade
    0.08
     deadlines
    0.08
    兼职
    0.08
     rocker
    0.08
     कीमत
    0.08
    Activations Density 0.113%

    No Known Activations