© 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. 65425
    Prev
    Next
    INDEX
    Explanations

    least

    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
     яс
    -0.08
     lucid
    -0.08
     to
    -0.07
     richten
    -0.07
    з
    -0.07
     affordability
    -0.07
    '
    -0.07
    भ
    -0.07
    nice
    -0.07
     tranquility
    -0.07
    POSITIVE LOGITS
     excludes
    0.10
     rejects
    0.09
     rejecting
    0.09
     reject
    0.09
    Reject
    0.08
     discarded
    0.08
     Reject
    0.08
    .exclude
    0.08
     discard
    0.08
     Fail
    0.08
    Activations Density 0.045%

    No Known Activations