Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44577
    Prev
    Next
    INDEX
    Explanations

    source

    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
     distortion
    -0.08
     chegaram
    -0.08
    弟
    -0.07
     distort
    -0.07
    -0.07
     대표
    -0.07
     Polic
    -0.07
     Drag
    -0.07
     యొక్క
    -0.07
     Beijing
    -0.07
    POSITIVE LOGITS
    יפוש
    0.11
     یافت
    0.10
     پیدا
    0.10
     որոն
    0.10
     löyt
    0.09
    公开
    0.09
     FO
    0.09
     найти
    0.09
     મેળવ
    0.09
    获取
    0.09
    Activations Density 0.029%

    No Known Activations