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. 111823
    Prev
    Next
    INDEX
    Explanations

    bell rings

    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
     Fry
    -0.08
     qol
    -0.07
     bier
    -0.07
    ്റെ
    -0.07
     Niet
    -0.07
     Detox
    -0.07
     seguro
    -0.07
    -0.07
     exclusivo
    -0.07
     gast
    -0.07
    POSITIVE LOGITS
     ignite
    0.10
     پایان
    0.10
    開始
    0.09
    开始
    0.09
    終了
    0.09
     دقیقه
    0.09
    締
    0.09
    钟
    0.08
     immin
    0.08
    结束
    0.08
    Activations Density 0.025%

    No Known Activations