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. 106282
    Prev
    Next
    INDEX
    Explanations

    This

    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
     vys
    -0.09
    主页
    -0.09
    二维码
    -0.09
     honeymoon
    -0.08
     pince
    -0.08
     consola
    -0.08
     Deloitte
    -0.08
    โหลด
    -0.08
     kork
    -0.08
    helo
    -0.08
    POSITIVE LOGITS
    "
    0.09
    =
    0.08
    ik
    0.08
    Given
    0.08
    -
    0.08
    5
    0.08
    4
    0.08
    _
    0.08
    -e
    0.08
    i
    0.08
    Activations Density 0.106%

    No Known Activations