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

    Neuronpedia

    APICircuit 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. 12984
    Prev
    Next
    INDEX
    Explanations

    excel sheets

    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
    úd
    -0.08
    dule
    -0.08
    .#
    -0.07
    রা
    -0.07
     Lago
    -0.07
     MDF
    -0.07
    ►
    -0.07
    未经
    -0.07
     bre
    -0.07
     FM
    -0.07
    POSITIVE LOGITS
     удовольствием
    0.08
     milliers
    0.08
    ,很
    0.08
    快乐
    0.07
     agak
    0.07
    asit
    0.07
     ?)
    0.07
    _ASSOC
    0.07
     renter
    0.07
    inji
    0.07
    Activations Density 0.000%

    No Known Activations