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. 106075
    Prev
    Next
    INDEX
    Explanations

    Visual novel script continuation

    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
    ifetime
    -0.09
     востреб
    -0.09
     жит
    -0.08
     жизн
    -0.08
     yaşayan
    -0.08
     срока
    -0.08
     сроки
    -0.08
     विकसित
    -0.08
     vigente
    -0.08
     профилакти
    -0.08
    POSITIVE LOGITS
    讲话
    0.13
     বক্তব্য
    0.11
     replies
    0.11
     الحوار
    0.10
     declaraciones
    0.10
     ಮಾತನಾಡ
    0.10
     বক্ত
    0.10
     സംസാര
    0.10
    回答
    0.10
     responses
    0.10
    Activations Density 0.041%

    No Known Activations