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. 58503
    Prev
    Next
    INDEX
    Explanations

    desires or objectives

    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
     convertible
    -0.08
     comunic
    -0.08
     verder
    -0.07
     equivalents
    -0.07
     ____
    -0.07
     fle
    -0.07
     wirk
    -0.07
     incapable
    -0.07
     Vereinig
    -0.07
     echten
    -0.07
    POSITIVE LOGITS
     استان
    0.07
     minimize
    0.07
     mı
    0.07
     investigates
    0.07
    ställ
    0.07
     выяс
    0.07
    āk
    0.07
     deseja
    0.07
     بررسی
    0.07
    pictured
    0.07
    Activations Density 0.118%

    No Known Activations