© 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. 11-RESID-POST-AA
    11. 43022
    Prev
    Next
    INDEX
    Explanations

    that, comma

    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
    izado
    -0.09
     läuft
    -0.09
     (=
    -0.09
    istic
    -0.09
     else's
    -0.09
     deducted
    -0.08
    是多少
    -0.08
     nostru
    -0.08
     vona
    -0.08
     назад
    -0.08
    POSITIVE LOGITS
     insanlar
    0.09
     современные
    0.08
     важно
    0.08
     excessive
    0.08
     extreme
    0.08
     ಒ
    0.07
     companies
    0.07
     SMEs
    0.07
     employers
    0.07
     disparities
    0.07
    Activations Density 0.105%

    No Known Activations