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. 30679
    Prev
    Next
    INDEX
    Explanations

    mobile network technologies

    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
     بچ
    -0.08
     gos
    -0.07
     Guidance
    -0.07
     管
    -0.07
    .register
    -0.07
    ftware
    -0.07
    ieën
    -0.07
     guidance
    -0.07
     MANAGEMENT
    -0.07
    金额
    -0.07
    POSITIVE LOGITS
     combatt
    0.08
     trolls
    0.08
     infil
    0.08
     splice
    0.07
     সালের
    0.07
    এস
    0.07
     objs
    0.07
    ())))
    0.07
    description
    0.07
    отив
    0.07
    Activations Density 0.008%

    No Known Activations