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. 43771
    Prev
    Next
    INDEX
    Explanations

    reader

    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
     Coach
    -0.08
     prayed
    -0.08
     instructional
    -0.08
     preached
    -0.08
     coach
    -0.08
     spear
    -0.08
     escenarios
    -0.08
    promotion
    -0.07
     coached
    -0.07
    _reporting
    -0.07
    POSITIVE LOGITS
     decompress
    0.09
    ISE
    0.08
     decom
    0.08
    (reader
    0.08
     metall
    0.08
    	reader
    0.08
     vintage
    0.07
     floppy
    0.07
    Cur
    0.07
    isor
    0.07
    Activations Density 0.003%

    No Known Activations