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. 112924
    Prev
    Next
    INDEX
    Explanations

    identity

    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
    )Math
    -0.08
     rare
    -0.08
     MHz
    -0.08
     perfor
    -0.08
    nibus
    -0.08
    submenu
    -0.07
     spann
    -0.07
    MHz
    -0.07
    (span
    -0.07
     spal
    -0.07
    POSITIVE LOGITS
     enviados
    0.08
     Baxter
    0.08
     casually
    0.08
     GPT
    0.08
    Bot
    0.07
    GPT
    0.07
     принадлеж
    0.07
     كب
    0.07
     حال
    0.07
     الفنية
    0.07
    Activations Density 0.010%

    No Known Activations