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

    Neuronpedia

    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. 44557
    Prev
    Next
    INDEX
    Explanations

    component

    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
    峰
    -0.09
     അത
    -0.08
     downhill
    -0.08
     CAPTCHA
    -0.08
     oploss
    -0.08
    AREN
    -0.08
     recession
    -0.07
     കുറ
    -0.07
     mite
    -0.07
    ABCDEFGHIJKLMNOP
    -0.07
    POSITIVE LOGITS
     इसी
    0.08
    组件
    0.08
    (component
    0.08
    (Component
    0.07
    .attach
    0.07
     realistically
    0.07
     exposing
    0.07
    @Component
    0.07
    God
    0.07
    (transform
    0.07
    Activations Density 0.002%

    No Known Activations