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. 88076
    Prev
    Next
    INDEX
    Explanations

    acetaminophen

    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
    爷
    -0.08
    ətlər
    -0.08
     biodivers
    -0.08
     методы
    -0.08
    acular
    -0.07
     Darwin
    -0.07
     doubt
    -0.07
    ale
    -0.07
     noticias
    -0.07
    atellite
    -0.07
    POSITIVE LOGITS
    Safe
    0.09
     mangan
    0.09
     Guitar
    0.08
     Safe
    0.08
    .safe
    0.08
     safe
    0.08
    163
    0.08
     الجانب
    0.08
     analges
    0.08
    ريل
    0.08
    Activations Density 0.002%

    No Known Activations