© 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. 68174
    Prev
    Next
    INDEX
    Explanations

    Fatty acids and chain length

    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
     उपाय
    -0.09
    Analytics
    -0.08
    启
    -0.08
     analytics
    -0.08
     proactive
    -0.08
    analytics
    -0.08
     concierge
    -0.07
     emailed
    -0.07
    metrics
    -0.07
     elections
    -0.07
    POSITIVE LOGITS
     aromatic
    0.14
     acidic
    0.13
     molé
    0.12
     carbohydrates
    0.12
     molecules
    0.12
     ligand
    0.12
     amino
    0.12
     compounds
    0.12
     carbohydrate
    0.12
     proteins
    0.11
    Activations Density 0.013%

    No Known Activations