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. 45072
    Prev
    Next
    INDEX
    Explanations

    prose

    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
    ுத
    -0.09
     معاملات
    -0.08
     Tanya
    -0.08
    ுத்த
    -0.07
     Son
    -0.07
     incentives
    -0.07
     Slav
    -0.07
     decimals
    -0.07
     uro
    -0.07
    宿
    -0.07
    POSITIVE LOGITS
    ™
    0.12
    ™,
    0.10
     adlı
    0.09
    ®
    0.09
     कहल
    0.08
    III
    0.08
     biệt
    0.08
    ®.
    0.08
    ®,
    0.08
     అనే
    0.07
    Activations Density 0.426%

    No Known Activations