© 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. 91768
    Prev
    Next
    INDEX
    Explanations

    buffalo

    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
     bane
    -0.08
     Hak
    -0.07
     bothers
    -0.07
     سک
    -0.07
     nes
    -0.07
    bane
    -0.07
     �
    -0.07
    �
    -0.07
     tary
    -0.07
    SON
    -0.07
    POSITIVE LOGITS
    .agent
    0.08
     Chow
    0.08
    客
    0.08
     relic
    0.08
    uated
    0.07
    _agent
    0.07
     Lake
    0.07
     Cardinals
    0.07
     Rome
    0.07
     Gross
    0.07
    Activations Density 0.004%

    No Known Activations