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. 58629
    Prev
    Next
    INDEX
    Explanations

    warnings or advice

    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
     typo
    -0.09
     năng
    -0.08
    Bug
    -0.08
     illusion
    -0.08
    性能
    -0.08
    bug
    -0.08
    Tuple
    -0.08
    形成
    -0.08
     suç
    -0.08
    实力
    -0.08
    POSITIVE LOGITS
     contraind
    0.16
     precautions
    0.13
     противопоказ
    0.13
     advis
    0.13
     advisable
    0.11
     caution
    0.11
     therapy
    0.11
     осторож
    0.11
     Advis
    0.11
     advise
    0.11
    Activations Density 0.035%

    No Known Activations