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. 43210
    Prev
    Next
    INDEX
    Explanations

    Code implementation/algorithms

    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
    IBOutlet
    -0.09
    ↵↵
    -0.08
     goods
    -0.08
     troubleshooting
    -0.07
    }`
    -0.07
     کنید
    -0.07
    }
    -0.07
     نک
    -0.07
    】
    -0.07
    」という
    -0.07
    POSITIVE LOGITS
     механизм
    0.12
     internally
    0.11
     underlying
    0.10
     mechanisms
    0.10
     gebaseerd
    0.10
     Intern
    0.10
    源码
    0.09
     underneath
    0.09
    机制
    0.09
     essentiellement
    0.09
    Activations Density 0.040%

    No Known Activations