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. 56015
    Prev
    Next
    INDEX
    Explanations

    to

    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
    yllabus
    -0.09
    iall
    -0.08
    уществует
    -0.08
     domác
    -0.08
     degelijk
    -0.08
     Анд
    -0.08
     самим
    -0.08
     homeschool
    -0.08
     istic
    -0.07
     ση
    -0.07
    POSITIVE LOGITS
     bidra
    0.09
     thrive
    0.08
     Ing
    0.08
     contribuir
    0.08
     contribuer
    0.08
     contribu
    0.08
     atu
    0.08
    .Start
    0.08
     aportar
    0.08
     empresa
    0.07
    Activations Density 0.009%

    No Known Activations