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. 111784
    Prev
    Next
    INDEX
    Explanations

    period

    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
     الخ
    -0.09
     البلا
    -0.09
     النحاس
    -0.09
     lume
    -0.09
     dwell
    -0.08
     النوع
    -0.08
     الشي
    -0.08
     pô
    -0.08
     barn
    -0.08
     الطريقة
    -0.08
    POSITIVE LOGITS
    &q
    0.07
    AI
    0.07
    IOException
    0.07
    IO
    0.07
    IBM
    0.07
    �
    0.07
    אמר
    0.07
     Mercado
    0.07
     unwilling
    0.07
    疫情
    0.07
    Activations Density 0.001%

    No Known Activations