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. 75964
    Prev
    Next
    INDEX
    Explanations

    sin

    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
    িমাণ
    -0.07
     Hust
    -0.07
    吗
    -0.07
    जी
    -0.07
     incr
    -0.07
    处理
    -0.07
    伦理
    -0.07
    اه
    -0.07
    ии
    -0.07
    保护
    -0.07
    POSITIVE LOGITS
     bestowed
    0.09
     displaced
    0.08
     coff
    0.08
    reib
    0.08
    Calendar
    0.08
    kę
    0.08
     alli
    0.08
     eigene
    0.08
     Steck
    0.08
    aktar
    0.07
    Activations Density 0.019%

    No Known Activations