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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 30734
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ighting
    -0.08
     эффективность
    -0.08
     desempeño
    -0.08
    ggi
    -0.08
    jing
    -0.07
     используется
    -0.07
     extremo
    -0.07
    Drive
    -0.07
     качество
    -0.07
    ยน
    -0.07
    POSITIVE LOGITS
    朋友圈
    0.09
     consortium
    0.08
     canais
    0.08
     parliament
    0.08
     فريق
    0.08
     communities
    0.08
     communautés
    0.08
     activities
    0.08
     armies
    0.08
     المجتمع
    0.08
    Activations Density 0.074%

    No Known Activations