© 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. 25233
    Prev
    Next
    INDEX
    Explanations

    peer

    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
     cart
    -0.10
    治理
    -0.08
     감사
    -0.07
    .cart
    -0.07
    _cart
    -0.07
     stakeholder
    -0.07
    ارج
    -0.07
    (cart
    -0.07
     хо
    -0.07
     كرة
    -0.07
    POSITIVE LOGITS
     Atem
    0.08
     floors
    0.08
    iggers
    0.08
     temp
    0.07
     Paso
    0.07
     Sed
    0.07
    ates
    0.07
    .Log
    0.07
     Converter
    0.07
    пер
    0.07
    Activations Density 0.001%

    No Known Activations