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. 11928
    Prev
    Next
    INDEX
    Explanations

    necklace

    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
    tj
    -0.08
    esite
    -0.07
     Bere
    -0.07
     디
    -0.07
    Move
    -0.07
    aze
    -0.07
     flavor
    -0.07
    ако
    -0.07
    иши
    -0.07
     निर्ध
    -0.07
    POSITIVE LOGITS
     Gordon
    0.09
     Siam
    0.09
    搭
    0.08
     abordar
    0.08
     desped
    0.08
     �
    0.08
    .Autowired
    0.08
     Chu
    0.08
    \Fac
    0.08
     Zhou
    0.08
    Activations Density 0.005%

    No Known Activations