Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109903
    Prev
    Next
    INDEX
    Explanations

    json xml files

    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
     reprez
    -0.08
     asociado
    -0.08
    ftig
    -0.08
    ಎ
    -0.07
    fy
    -0.07
    روط
    -0.07
     okub
    -0.07
     represent
    -0.07
    arge
    -0.07
    ರ್ಶ
    -0.07
    POSITIVE LOGITS
     goût
    0.08
     قدرة
    0.08
     الطلب
    0.08
     تقنية
    0.08
     ameaça
    0.08
     том
    0.08
    зі
    0.08
    0.08
     способность
    0.07
     صحة
    0.07
    Activations Density 0.002%

    No Known Activations