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. 43770
    Prev
    Next
    INDEX
    Explanations

    scrolling

    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
    ボ
    -0.08
     ボ
    -0.08
     Martínez
    -0.07
    -Pl
    -0.07
    (if
    -0.07
     feugiat
    -0.07
     നിന്ന
    -0.07
     Won
    -0.07
     Martinez
    -0.07
     Pvt
    -0.07
    POSITIVE LOGITS
     contas
    0.09
     vali
    0.08
     đến
    0.08
    Да
    0.07
    чә
    0.07
     sâu
    0.07
     hira
    0.07
    �
    0.07
     diseñ
    0.07
     propr
    0.07
    Activations Density 0.003%

    No Known Activations