© 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. 129460
    Prev
    Next
    INDEX
    Explanations

    icosahedron

    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
     المستخدمة
    -0.08
     arrière
    -0.08
     SUS
    -0.07
     Aussch
    -0.07
    正常
    -0.07
    érées
    -0.07
     দৃ
    -0.07
     لقد
    -0.07
     الإنترنت
    -0.07
     предлагаем
    -0.07
    POSITIVE LOGITS
    _guard
    0.09
     guards
    0.08
     कुल
    0.08
    .Count
    0.08
    -occ
    0.08
    tect
    0.08
    /detail
    0.07
     apoi
    0.07
    boy
    0.07
     tota
    0.07
    Activations Density 0.001%

    No Known Activations