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. 111807
    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
    ats
    -0.08
    owy
    -0.08
    货
    -0.07
    实现
    -0.07
    有效
    -0.07
    各种
    -0.07
    厂
    -0.07
    进行
    -0.07
    上市
    -0.07
    ோர்
    -0.07
    POSITIVE LOGITS
    ضرورة
    0.09
     hingegen
    0.09
     സമീപ
    0.09
    Palindrome
    0.08
    intig
    0.08
    Corr
    0.08
    _PCM
    0.08
     संक्रम
    0.08
    때
    0.08
    alik
    0.08
    Activations Density 0.001%

    No Known Activations