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. 11-RESID-POST-AA
    6. 106129
    Prev
    Next
    INDEX
    Explanations

    arithmetic problems

    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
    bels
    -0.09
    diagn
    -0.08
    directive
    -0.08
     directora
    -0.08
    案件
    -0.07
    irango
    -0.07
     juntas
    -0.07
    -0.07
     Alleg
    -0.07
    ிடம்
    -0.07
    POSITIVE LOGITS
    _plus
    0.09
     ακόμη
    0.08
     plus
    0.08
     saja
    0.08
     lub
    0.08
    -plus
    0.08
     எழ
    0.08
     vann
    0.07
     তুলে
    0.07
     плюс
    0.07
    Activations Density 0.056%

    No Known Activations