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. 58754
    Prev
    Next
    INDEX
    Explanations

    arbitration legal disputes

    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
     replication
    -0.08
    Copy
    -0.08
    	write
    -0.08
     conversions
    -0.08
    junction
    -0.08
     Kr
    -0.07
    X
    -0.07
     Copy
    -0.07
     copy
    -0.07
    	copy
    -0.07
    POSITIVE LOGITS
     appointed
    0.10
     investigator
    0.09
     accredited
    0.09
     knowledgeable
    0.09
    -appointed
    0.09
     Accredited
    0.09
    聘
    0.08
     مكتب
    0.08
     반드시
    0.08
    кого
    0.08
    Activations Density 0.018%

    No Known Activations