© 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. 79130
    Prev
    Next
    INDEX
    Explanations

    priming

    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
    kend
    -0.08
     alba
    -0.07
     penetration
    -0.07
    (plugin
    -0.07
    ouf
    -0.07
     Gutenberg
    -0.07
     plugin
    -0.07
     sita
    -0.07
     steadily
    -0.07
     جار
    -0.07
    POSITIVE LOGITS
     induce
    0.08
     миллий
    0.08
     colleges
    0.08
     juice
    0.08
     Receive
    0.08
    Roster
    0.08
    På
    0.08
    uintes
    0.08
     шеш
    0.07
     אותו
    0.07
    Activations Density 0.000%

    No Known Activations