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. 15-RESID-POST-AA
    6. 19072
    Prev
    Next
    INDEX
    Explanations

    -shirt

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Attend
    -0.08
    Cuenta
    -0.08
    actividad
    -0.08
    Añ
    -0.08
     Atlet
    -0.08
    Manage
    -0.08
    Tenant
    -0.08
     tournaments
    -0.08
     Ansprechpartner
    -0.08
    five
    -0.08
    POSITIVE LOGITS
     дизайн
    0.11
     디자인
    0.10
     схема
    0.10
     desain
    0.09
     схем
    0.09
     дизай
    0.09
     تصميم
    0.09
     Scheme
    0.09
     ontwerpen
    0.09
     ವಿನ
    0.09
    Activations Density 0.007%

    No Known Activations