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. 30673
    Prev
    Next
    INDEX
    Explanations

    class loader

    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
    ellipse
    -0.11
     ellipse
    -0.10
    stroke
    -0.09
    Ellipse
    -0.08
     pursuit
    -0.08
     rowing
    -0.08
     bearish
    -0.08
     breast
    -0.08
     elliptical
    -0.08
     extremes
    -0.08
    POSITIVE LOGITS
    加载
    0.15
    _LOAD
    0.12
    .loaded
    0.12
    	load
    0.12
    _loaded
    0.11
     unload
    0.11
    _load
    0.11
     loader
    0.11
    .load
    0.11
     unloading
    0.11
    Activations Density 0.016%

    No Known Activations