© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 108136
    Prev
    Next
    INDEX
    Explanations

    Healthcare systems

    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
     inequality
    -0.09
    _PARSE
    -0.08
     inconvenience
    -0.07
    glyph
    -0.07
    kante
    -0.07
    javascript
    -0.07
    splice
    -0.07
     torna
    -0.07
     inequalities
    -0.07
    _COLL
    -0.07
    POSITIVE LOGITS
    全民
    0.08
     theatres
    0.08
     predominant
    0.08
     recruiters
    0.08
    icina
    0.08
    ांक
    0.07
    štu
    0.07
    יף
    0.07
     conscience
    0.07
     clinician
    0.07
    Activations Density 0.006%

    No Known Activations