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. 23-RESID-POST-AA
    6. 98207
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _finished
    -0.09
    faf
    -0.09
    \v
    -0.09
    -foot
    -0.09
     reproduce
    -0.09
     reproduced
    -0.09
    iesen
    -0.08
    _finish
    -0.08
     continuing
    -0.08
    _cnt
    -0.08
    POSITIVE LOGITS
     الاستخدام
    0.11
    User
    0.09
    uncios
    0.09
     Implementation
    0.09
     사용자
    0.09
     உங்கள்
    0.09
    Usage
    0.09
     Kullan
    0.08
     Usage
    0.08
    用户
    0.08
    Activations Density 0.256%

    No Known Activations