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. 30685
    Prev
    Next
    INDEX
    Explanations

    Foreign characters

    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
     ux
    -0.09
     Crem
    -0.08
     ROB
    -0.08
     xbox
    -0.08
     живот
    -0.08
     CBS
    -0.08
     CRO
    -0.08
     Bov
    -0.08
     Batman
    -0.08
     Omaha
    -0.08
    POSITIVE LOGITS
    ‹
    0.08
     turut
    0.08
    署
    0.08
    晰
    0.08
    Regardless
    0.08
    彰
    0.08
    seguir
    0.08
     supplies
    0.08
        
    0.07
     distinctly
    0.07
    Activations Density 0.014%

    No Known Activations