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. 88318
    Prev
    Next
    INDEX
    Explanations

    speaking

    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
     Forder
    -0.09
     Chávez
    -0.08
     venc
    -0.08
     Trap
    -0.08
    ritz
    -0.08
    陷
    -0.08
    trap
    -0.08
     永
    -0.07
    蓝
    -0.07
    -0.07
    POSITIVE LOGITS
     кезінде
    0.09
    �
    0.08
    �
    0.08
     положении
    0.08
     pohod
    0.08
    ktu
    0.08
     полноцен
    0.08
     impacted
    0.08
     комфорт
    0.08
     accommodation
    0.08
    Activations Density 0.005%

    No Known Activations