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. 102840
    Prev
    Next
    INDEX
    Explanations

    out

    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
    зам
    -0.08
    修改
    -0.07
     corrected
    -0.07
    分别
    -0.07
     correction
    -0.07
    设施
    -0.07
    _bal
    -0.07
     corrections
    -0.07
    _sta
    -0.07
    ബ
    -0.07
    POSITIVE LOGITS
     crowded
    0.12
     amidst
    0.11
     destacar
    0.10
     경쟁
    0.10
    among
    0.10
    竞争
    0.10
    との差
    0.10
    Uni
    0.10
    Among
    0.10
     среди
    0.09
    Activations Density 0.034%

    No Known Activations