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. 77315
    Prev
    Next
    INDEX
    Explanations

    ‑

    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
     Meme
    -0.09
     Spider
    -0.09
    alty
    -0.09
     Twilight
    -0.08
     Hem
    -0.08
    Hem
    -0.08
    Spider
    -0.08
     Gegend
    -0.08
     cringe
    -0.08
     MW
    -0.08
    POSITIVE LOGITS
     وراء
    0.09
     et
    0.08
    [source
    0.08
    _a
    0.07
     كان
    0.07
     ôl
    0.07
     början
    0.07
     જોઈએ
    0.07
     المصدر
    0.07
    0.07
    Activations Density 0.002%

    No Known Activations