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. 43792
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     hohe
    -0.08
     Wikipedia
    -0.08
     Genau
    -0.08
     hoge
    -0.08
     genau
    -0.07
     hoher
    -0.07
    কল
    -0.07
     ano
    -0.07
     कॉल
    -0.07
    America
    -0.07
    POSITIVE LOGITS
     ہوگی
    0.09
    贯
    0.08
     бәл
    0.08
     تھیں
    0.08
    šev
    0.08
    说道
    0.08
     ہوج
    0.08
     (.
    0.08
     تفا
    0.08
    -bs
    0.08
    Activations Density 0.051%

    No Known Activations