© 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. 78857
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    .Lo
    -0.08
    رج
    -0.07
    except
    -0.07
    auc
    -0.07
    'au
    -0.07
    ,max
    -0.07
    ayes
    -0.07
     today
    -0.07
    (car
    -0.07
    'en
    -0.07
    POSITIVE LOGITS
    .extra
    0.08
    _EXTRA
    0.08
     withheld
    0.08
     adicionales
    0.08
     अतिरिक्त
    0.08
    Excluded
    0.08
    sertations
    0.08
     CFO
    0.08
     issus
    0.08
    тық
    0.07
    Activations Density 0.067%

    No Known Activations