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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 31149
    Prev
    Next
    INDEX
    Explanations

    barcodes

    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
    微软雅黑
    -0.10
     முதல
    -0.08
     plazas
    -0.08
     cav
    -0.08
     piir
    -0.08
     ciddi
    -0.08
     Infragistics
    -0.08
    期限
    -0.08
     bess
    -0.08
    ложения
    -0.08
    POSITIVE LOGITS
     airt
    0.09
    ventory
    0.08
    /id
    0.08
     workflow
    0.08
     confirms
    0.08
    _id
    0.08
    /down
    0.08
    _ID
    0.08
    /controller
    0.08
    .rf
    0.08
    Activations Density 0.005%

    No Known Activations