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. 19122
    Prev
    Next
    INDEX
    Explanations

    known

    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
     বা
    -0.10
    -turn
    -0.10
     ਜਾਂ
    -0.10
    -maker
    -0.09
    -second
    -0.09
     কখন
    -0.09
    -dr
    -0.09
     diğer
    -0.09
     или
    -0.09
    或
    -0.09
    POSITIVE LOGITS
     sebuah
    0.09
     Proposition
    0.09
     имеется
    0.08
    Notation
    0.08
     equation
    0.08
    Equation
    0.08
     ένα
    0.08
     fundamentally
    0.08
    Elementary
    0.08
     Equation
    0.08
    Activations Density 0.022%

    No Known Activations