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. 11812
    Prev
    Next
    INDEX
    Explanations

    hour

    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
     Eternal
    -0.08
    kana
    -0.08
    Fatal
    -0.08
    .realm
    -0.08
     bañ
    -0.08
     betyd
    -0.07
    Finish
    -0.07
    орту
    -0.07
     kapt
    -0.07
     פארשט
    -0.07
    POSITIVE LOGITS
    ன்று
    0.08
     reflexão
    0.08
     Cler
    0.07
     cling
    0.07
    ophone
    0.07
     clinker
    0.07
     Dö
    0.07
    iar
    0.07
    居民
    0.07
    าจะ
    0.07
    Activations Density 0.011%

    No Known Activations