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. 12036
    Prev
    Next
    INDEX
    Explanations

    }$

    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
    科技
    -0.09
    税
    -0.08
    市
    -0.07
    技术
    -0.07
    神
    -0.07
    生活
    -0.07
     baths
    -0.07
     Math
    -0.07
    纪
    -0.07
     Nah
    -0.07
    POSITIVE LOGITS
    ्लिम
    0.09
    CATEGORY
    0.09
    VALID
    0.09
     arac
    0.08
     VALID
    0.08
     durum
    0.08
    .subplots
    0.08
     surat
    0.08
     validator
    0.08
     frat
    0.08
    Activations Density 0.023%

    No Known Activations