© 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. 24676
    Prev
    Next
    INDEX
    Explanations

    SQL queries

    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
     dith
    -0.08
     vell
    -0.08
    scratch
    -0.08
     membantu
    -0.08
    _Adjustor
    -0.07
    #ifdef
    -0.07
     имеет
    -0.07
    翼
    -0.07
     instinct
    -0.07
    #endif
    -0.07
    POSITIVE LOGITS
     busiest
    0.11
    Customers
    0.11
    Employees
    0.10
     Mostrar
    0.10
     查询
    0.10
    Departments
    0.10
     查看
    0.09
     promedio
    0.09
     조회
    0.09
     Departamento
    0.09
    Activations Density 0.018%

    No Known Activations