© 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. 54430
    Prev
    Next
    INDEX
    Explanations

    field

    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
     polit
    -0.08
     illusion
    -0.08
     emf
    -0.08
     amper
    -0.08
     aza
    -0.08
     hailed
    -0.07
    Sehr
    -0.07
     architect
    -0.07
    IPO
    -0.07
     ತಿಳ
    -0.07
    POSITIVE LOGITS
    coffee
    0.08
    wu
    0.08
    yen
    0.08
    青春
    0.08
    _FACE
    0.07
     прям
    0.07
    expr
    0.07
    ,text
    0.07
    覆盖
    0.07
    ock
    0.07
    Activations Density 0.001%

    No Known Activations