© 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. 723
    Prev
    Next
    INDEX
    Explanations

    Table data separators

    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
     sinal
    -0.08
     helt
    -0.07
     unob
    -0.07
     maar
    -0.07
     instead
    -0.07
     unor
    -0.07
     Freude
    -0.07
    -s
    -0.07
     flotation
    -0.07
    exclusive
    -0.07
    POSITIVE LOGITS
     famously
    0.10
     famed
    0.10
     Explained
    0.09
     famosos
    0.09
    经典
    0.08
     famous
    0.08
     explicó
    0.08
     klasik
    0.08
     clásicos
    0.08
     iconic
    0.08
    Activations Density 0.078%

    No Known Activations