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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19411
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     "**
    -0.10
     geschikte
    -0.09
    盒彩
    -0.09
    мотрите
    -0.09
    ıkl
    -0.09
    หรับ
    -0.09
    oneka
    -0.08
    -match
    -0.08
    ેસ
    -0.08
    look
    -0.08
    POSITIVE LOGITS
     obviously
    0.11
     tempt
    0.10
     intuition
    0.09
     tempting
    0.09
     temptation
    0.08
     tempted
    0.08
     naive
    0.08
     na
    0.08
     upe
    0.08
     the
    0.08
    Activations Density 0.067%

    No Known Activations