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. 43854
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
    呢
    -0.09
     Lover
    -0.09
     nessa
    -0.08
     faptul
    -0.08
     இந்த
    -0.08
    这个
    -0.07
     tento
    -0.07
    Bm
    -0.07
     berdasarkan
    -0.07
     aufreg
    -0.07
    POSITIVE LOGITS
     iff
    0.09
    0.08
    FT
    0.08
     impair
    0.08
     AMS
    0.07
    matic
    0.07
    ⇒
    0.07
     termed
    0.07
     journal
    0.07
    ഥ
    0.07
    Activations Density 0.352%

    No Known Activations