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. 30712
    Prev
    Next
    INDEX
    Explanations

    about

    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
    满意
    -0.09
     agradable
    -0.09
     Yep
    -0.08
     payable
    -0.08
    Ist
    -0.07
     सुव
    -0.07
     만족
    -0.07
    详
    -0.07
     версии
    -0.07
     удовлетвор
    -0.07
    POSITIVE LOGITS
     Minis
    0.10
    ที่จะ
    0.09
     opportunity
    0.09
     prospects
    0.08
     poter
    0.08
     возможность
    0.08
     possibility
    0.08
     oportunidade
    0.08
     إمكانية
    0.08
    stehen
    0.08
    Activations Density 0.015%

    No Known Activations