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. 15-RESID-POST-AA
    6. 19489
    Prev
    Next
    INDEX
    Explanations

    can

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ১
    -0.09
    Base
    -0.08
    凤凰
    -0.08
    ště
    -0.08
    یہ
    -0.08
    _FL
    -0.08
     twenty
    -0.08
    配
    -0.08
     单
    -0.08
    菲律宾
    -0.08
    POSITIVE LOGITS
     وحتى
    0.09
     مثلا
    0.09
     ואף
    0.08
     what
    0.08
     unhas
    0.08
     pretend
    0.08
     supposedly
    0.08
     nonexistent
    0.08
     potentially
    0.08
     supposed
    0.07
    Activations Density 0.002%

    No Known Activations