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. 60748
    Prev
    Next
    INDEX
    Explanations

    session management (code)

    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
     extinct
    -0.08
    endaft
    -0.08
     鹤
    -0.08
     spoiler
    -0.08
     solitaire
    -0.08
    erd
    -0.08
    โด
    -0.08
     المهم
    -0.07
    _positive
    -0.07
    gefügt
    -0.07
    POSITIVE LOGITS
    (sql
    0.09
     Banco
    0.09
    .Session
    0.08
    (iterator
    0.08
    (ms
    0.08
    .Database
    0.08
    (scope
    0.08
    (exception
    0.08
     sessions
    0.08
    .Resource
    0.08
    Activations Density 0.005%

    No Known Activations