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. 42123
    Prev
    Next
    INDEX
    Explanations

    oy

    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
    吕
    -0.10
    /Public
    -0.10
     һәл
    -0.09
    idingen
    -0.09
     ცოდ
    -0.09
     百度
    -0.09
    ებების
    -0.08
     зид
    -0.08
     speziell
    -0.08
     სი
    -0.08
    POSITIVE LOGITS
    �
    0.09
    100
    0.08
    ̌
    0.08
    f
    0.07
    Card
    0.07
    -like
    0.07
    mist
    0.07
    _
    0.07
    ्ग
    0.07
    1
    0.07
    Activations Density 0.118%

    No Known Activations