© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 47856
    Prev
    Next
    INDEX
    Explanations

    population numbers

    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
     cops
    -0.08
    .Customer
    -0.08
    <Customer
    -0.08
     relates
    -0.08
     precinct
    -0.08
     고객
    -0.08
     кадров
    -0.08
    .Redirect
    -0.07
    punt
    -0.07
     gritty
    -0.07
    POSITIVE LOGITS
    全球
    0.23
     worldwide
    0.22
     weltweit
    0.22
     全球
    0.20
     wereldwijd
    0.20
     mundial
    0.20
     mondial
    0.19
     duniya
    0.19
     mondiale
    0.19
     العالم
    0.18
    Activations Density 0.181%

    No Known Activations