© 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. 108361
    Prev
    Next
    INDEX
    Explanations

    4

    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
    .Inet
    -0.08
     произошло
    -0.08
     היה
    -0.08
     vermo
    -0.08
    _horizontal
    -0.08
    .START
    -0.08
     ocurrió
    -0.08
     cięż
    -0.08
     balk
    -0.08
     elected
    -0.07
    POSITIVE LOGITS
    生成
    0.07
    شرة
    0.07
     persona
    0.07
    illation
    0.07
    etjes
    0.07
     cors
    0.07
    トップ
    0.07
     compil
    0.07
     estate
    0.07
     parenting
    0.07
    Activations Density 0.010%

    No Known Activations