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. 46436
    Prev
    Next
    INDEX
    Explanations

    Review

    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
     fixture
    -0.08
    Degrees
    -0.08
     Degrees
    -0.08
    Yi
    -0.08
     functionality
    -0.07
    }><
    -0.07
     degrees
    -0.07
     obligatorio
    -0.07
     pup
    -0.07
    咪
    -0.07
    POSITIVE LOGITS
     inzichten
    0.09
     પ્રવ
    0.09
    观点
    0.09
    刊
    0.09
    帖子
    0.08
     પોસ્ટ
    0.08
     ASE
    0.08
     প্রব
    0.08
     प्रव
    0.08
    相关文章
    0.08
    Activations Density 0.003%

    No Known Activations