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. 12111
    Prev
    Next
    INDEX
    Explanations

    other

    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
     fg
    -0.08
     moll
    -0.08
     foreground
    -0.08
    Allocator
    -0.08
    foreground
    -0.08
    ④
    -0.08
    asi
    -0.07
    Descending
    -0.07
     вын
    -0.07
     wysoko
    -0.07
    POSITIVE LOGITS
    Knowledge
    0.08
    未知
    0.08
     وراء
    0.08
    روفة
    0.08
    (',
    0.08
     knowledge
    0.08
     Knowledge
    0.08
    -json
    0.08
    ეობა
    0.07
     Practice
    0.07
    Activations Density 0.004%

    No Known Activations