© 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. 95345
    Prev
    Next
    INDEX
    Explanations

    intuition

    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
     newspaper
    -0.08
     resistente
    -0.08
     nach
    -0.07
     politique
    -0.07
     утеп
    -0.07
     ihr
    -0.07
     veilig
    -0.07
     tallest
    -0.07
     Nig
    -0.07
    еде
    -0.07
    POSITIVE LOGITS
     intuitive
    0.12
     experiential
    0.11
     intuition
    0.11
     intuit
    0.10
    即时
    0.10
     तत्काल
    0.10
     firsthand
    0.10
     срод
    0.09
     instinct
    0.09
     subconscious
    0.09
    Activations Density 0.024%

    No Known Activations