Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 88253
    Prev
    Next
    INDEX
    Explanations

    mov

    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
    半年
    -0.09
     volcan
    -0.08
     lagi
    -0.08
    /Admin
    -0.08
    有限公司
    -0.08
     য
    -0.08
    /月
    -0.08
     volcanic
    -0.08
     Volcano
    -0.08
     buckle
    -0.08
    POSITIVE LOGITS
    zx
    0.09
     устанавли
    0.08
     eax
    0.08
    String
    0.08
     объекта
    0.08
    ecto
    0.07
     значение
    0.07
    .ie
    0.07
    .force
    0.07
     antecip
    0.07
    Activations Density 0.001%

    No Known Activations