© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 85
    Prev
    Next
    INDEX
    Explanations

    accounting and taxes

    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
     হাঁ
    -0.07
     tripod
    -0.07
     ster
    -0.07
    เห
    -0.07
     freie
    -0.07
    onie
    -0.07
     invariant
    -0.07
     HTML
    -0.07
     stack
    -0.07
    elah
    -0.07
    POSITIVE LOGITS
    .ends
    0.09
    	date
    0.09
     país
    0.09
     jurisd
    0.09
     относится
    0.09
     события
    0.08
    belongs
    0.08
     nationality
    0.08
    DATE
    0.08
     mérito
    0.08
    Activations Density 0.012%

    No Known Activations