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. 120271
    Prev
    Next
    INDEX
    Explanations

    mathematical functions

    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
     Benny
    -0.08
     बुधवार
    -0.08
    Enrollment
    -0.08
     adjud
    -0.08
     sept
    -0.08
    _enqueue
    -0.08
     Sept
    -0.08
     ballots
    -0.08
     bats
    -0.08
     badminton
    -0.08
    POSITIVE LOGITS
     exponent
    0.14
    Exponent
    0.11
     scaling
    0.11
     Scaling
    0.10
     ln
    0.10
     exponential
    0.10
     expon
    0.10
     dimensional
    0.10
    指数
    0.10
    Scaling
    0.09
    Activations Density 0.035%

    No Known Activations