© 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. 95327
    Prev
    Next
    INDEX
    Explanations

    break

    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
     kennen
    -0.07
     posible
    -0.07
     Boko
    -0.07
    recogn
    -0.07
    _lv
    -0.07
    末
    -0.07
     eins
    -0.07
     recognition
    -0.07
     produit
    -0.07
    clus
    -0.06
    POSITIVE LOGITS
     pausa
    0.12
     વિર
    0.11
     ಮಧ್ಯ
    0.11
     meantime
    0.10
     halfway
    0.10
     pause
    0.10
    Pause
    0.10
     midway
    0.10
     وقف
    0.10
     منتصف
    0.09
    Activations Density 0.088%

    No Known Activations