© 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. 95780
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
     necessarily
    -0.08
    医院
    -0.08
     tumors
    -0.07
     volledige
    -0.07
     collo
    -0.07
     remodeling
    -0.07
     ranking
    -0.07
     coaches
    -0.07
    おります
    -0.07
     restriction
    -0.07
    POSITIVE LOGITS
     Sorted
    0.09
    Sorted
    0.09
     grouped
    0.08
     sorted
    0.08
    _CHANGED
    0.08
    _Group
    0.08
    [group
    0.08
     nära
    0.08
    "group
    0.08
    odi
    0.08
    Activations Density 0.004%

    No Known Activations