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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98510
    Prev
    Next
    INDEX
    Explanations

    Spawning and time to live

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    combat
    -0.10
    .Execution
    -0.09
     নাট
    -0.09
    execution
    -0.09
    Combat
    -0.09
     Combat
    -0.09
     combat
    -0.09
    -0.09
     dramat
    -0.08
     sewing
    -0.08
    POSITIVE LOGITS
     lifespan
    0.13
     lifetime
    0.11
     spawn
    0.11
     resp
    0.11
     Lifetime
    0.11
     destroys
    0.11
     destroy
    0.11
    寿
    0.11
     muncul
    0.10
    _resp
    0.10
    Activations Density 0.007%

    No Known Activations