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. 43229
    Prev
    Next
    INDEX
    Explanations

    soggy

    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
     berb
    -0.08
     ś
    -0.08
    لمة
    -0.08
    śl
    -0.08
     تت
    -0.07
     เช่น
    -0.07
     Exhibition
    -0.07
    λεί
    -0.07
    ॉक
    -0.07
    _MASK
    -0.07
    POSITIVE LOGITS
     unnatural
    0.09
     unnecessarily
    0.08
     unnecessary
    0.08
     Diskussion
    0.08
    ++++
    0.08
     beneden
    0.08
     мут
    0.08
     Worse
    0.08
     Verdict
    0.07
    NES
    0.07
    Activations Density 0.006%

    No Known Activations