© 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. 8084
    Prev
    Next
    INDEX
    Explanations

    Combinatorial enumeration

    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
     evidence
    -0.08
     interoperability
    -0.08
    ႔
    -0.08
     olor
    -0.08
     interoper
    -0.08
     års
    -0.08
     именно
    -0.07
     исчез
    -0.07
    asyon
    -0.07
     transparent
    -0.07
    POSITIVE LOGITS
     excursions
    0.09
    QUEUE
    0.09
    _QUEUE
    0.09
    Throughout
    0.09
     במהלך
    0.08
    Morgan
    0.08
     lest
    0.08
    drž
    0.08
     NEVER
    0.08
     Throughout
    0.08
    Activations Density 0.010%

    No Known Activations