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. 44185
    Prev
    Next
    INDEX
    Explanations

    .cpp and .c

    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
    _FACTOR
    -0.08
    'ac
    -0.08
    FACT
    -0.07
     appropri
    -0.07
    LL
    -0.07
    ഉ
    -0.07
     uso
    -0.07
     cult
    -0.07
    Four
    -0.07
     extraordinary
    -0.07
    POSITIVE LOGITS
     제출
    0.09
    /**/*.
    0.09
     файл
    0.09
    Compiled
    0.08
    弄
    0.08
     файла
    0.08
     السك
    0.08
    annels
    0.08
     Dependencies
    0.08
    chtig
    0.08
    Activations Density 0.003%

    No Known Activations