© 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. 95274
    Prev
    Next
    INDEX
    Explanations

    time intervals

    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
    <State
    -0.08
     barric
    -0.08
     Bend
    -0.08
     Ane
    -0.08
     oily
    -0.07
     Artes
    -0.07
     legitimacy
    -0.07
     lipid
    -0.07
    Injection
    -0.07
    Neem
    -0.07
    POSITIVE LOGITS
    （日
    0.10
    calendar
    0.10
     gran
    0.10
     timedelta
    0.10
    (interval
    0.09
     diário
    0.09
     calendar
    0.09
     coarse
    0.09
     옵션
    0.09
     календар
    0.08
    Activations Density 0.005%

    No Known Activations