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. 53898
    Prev
    Next
    INDEX
    Explanations

    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
     disguised
    -0.09
    .tmp
    -0.08
     bes
    -0.08
     exponentially
    -0.07
     imitation
    -0.07
     Jenn
    -0.07
    (em
    -0.07
     Sieg
    -0.07
     Illumin
    -0.07
     Stir
    -0.07
    POSITIVE LOGITS
     sqlalchemy
    0.11
    Orm
    0.10
    typeorm
    0.10
    .orm
    0.09
    Agregar
    0.09
     ORM
    0.09
     hql
    0.09
     orm
    0.09
    рых
    0.09
     agregar
    0.09
    Activations Density 0.005%

    No Known Activations