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. 65764
    Prev
    Next
    INDEX
    Explanations

    ">"

    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
    Ty
    -0.08
    遍
    -0.08
    -router
    -0.08
    -Re
    -0.07
    辽
    -0.07
    <|endoftext|>
    -0.07
    /L
    -0.07
    -0.07
    lit
    -0.07
    -0.07
    POSITIVE LOGITS
     nesses
    0.09
    =@
    0.09
     가능한
    0.09
     بينها
    0.09
     खबर
    0.09
     الطلب
    0.08
    가능
    0.08
     الأه
    0.08
     Antworten
    0.08
     soles
    0.08
    Activations Density 0.001%

    No Known Activations