Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 12972
    Prev
    Next
    INDEX
    Explanations

    Excel data models

    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
    Kn
    -0.08
     blocking
    -0.08
     fournisseur
    -0.08
    (block
    -0.07
     Ambassador
    -0.07
     যাতে
    -0.07
     Kn
    -0.07
    កម្ម
    -0.07
     Executors
    -0.07
     Afro
    -0.07
    POSITIVE LOGITS
    ặt
    0.08
     이루
    0.08
    .compile
    0.08
    MAIL
    0.07
     दर्ज
    0.07
    },↵↵
    0.07
     भूम
    0.07
     ï
    0.07
     isl
    0.07
    	goto
    0.07
    Activations Density 0.000%

    No Known Activations