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. 53010
    Prev
    Next
    INDEX
    Explanations

    security testing

    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
     亚洲
    -0.08
     좋아
    -0.08
     وعد
    -0.08
    .arraycopy
    -0.08
    .jsdelivr
    -0.08
     Asian
    -0.08
    在线视频
    -0.08
     yorum
    -0.08
    亚洲
    -0.07
    :image
    -0.07
    POSITIVE LOGITS
     공격
    0.12
     હુમ
    0.12
     ആക്രമ
    0.12
     saldır
    0.11
     vulnerabilities
    0.11
    Testing
    0.11
    攻击
    0.10
     atacante
    0.10
     malicious
    0.10
     attacker
    0.10
    Activations Density 0.015%

    No Known Activations