Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 324
    Prev
    Next
    INDEX
    Explanations

    adverb and verb suffixes

    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
    roid
    -0.08
    所以
    -0.08
    包装
    -0.08
    一句
    -0.07
    Maker
    -0.07
    roids
    -0.07
     culin
    -0.07
     روب
    -0.07
    物业
    -0.07
    主任
    -0.07
    POSITIVE LOGITS
     glare
    0.09
     linewidth
    0.09
     перем
    0.08
     amounts
    0.08
     swollen
    0.08
     Complexity
    0.08
    engl
    0.08
     complexity
    0.08
     Distance
    0.08
     delays
    0.08
    Activations Density 0.052%

    No Known Activations