© 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. 111417
    Prev
    Next
    INDEX
    Explanations

    Calculating weeks in a month

    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
     ખાતે
    -0.08
    명
    -0.08
    iol
    -0.08
    trusted
    -0.08
    Awesome
    -0.08
    ">(
    -0.08
    Bullet
    -0.08
     exclaimed
    -0.08
    Sink
    -0.07
    Syntax
    -0.07
    POSITIVE LOGITS
     promedio
    0.11
     నెల
    0.10
    平均
    0.10
     miesią
    0.10
     Months
    0.10
     months
    0.10
     weeks
    0.10
     menstrual
    0.09
     Ortalama
    0.09
    months
    0.09
    Activations Density 0.016%

    No Known Activations