© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 99446
    Prev
    Next
    INDEX
    Explanations

    carbon and steel

    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
    Obama
    -0.09
    Inclus
    -0.08
     President
    -0.08
    ಿತರ
    -0.08
     UNICEF
    -0.08
     compos
    -0.08
     shuffle
    -0.07
     Bale
    -0.07
     presidenta
    -0.07
     honoring
    -0.07
    POSITIVE LOGITS
     зуб
    0.08
     ];
    0.08
     };
    0.08
     olay
    0.08
     medicinal
    0.08
    isional
    0.08
     releases
    0.08
     pocket
    0.08
     cartridges
    0.07
     razum
    0.07
    Activations Density 0.004%

    No Known Activations