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. 112885
    Prev
    Next
    INDEX
    Explanations

    r

    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
    chart
    -0.08
     agradável
    -0.08
     servlet
    -0.08
     стратег
    -0.08
     Chart
    -0.08
    Mang
    -0.08
    표
    -0.07
    -chart
    -0.07
     varying
    -0.07
     요구
    -0.07
    POSITIVE LOGITS
     crowdfunding
    0.08
     yr
    0.08
     Thunder
    0.07
     leon
    0.07
     prol
    0.07
     egen
    0.07
     lef
    0.07
    omon
    0.07
     Political
    0.07
    .team
    0.07
    Activations Density 0.001%

    No Known Activations