© 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. 26185
    Prev
    Next
    INDEX
    Explanations

    Considering additional conditions

    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
     prema
    -0.09
     cinematic
    -0.08
    Shares
    -0.08
     soweit
    -0.08
     cyclist
    -0.07
     Али
    -0.07
    encji
    -0.07
     موجب
    -0.07
     samkvæmt
    -0.07
    reno
    -0.07
    POSITIVE LOGITS
     phantom
    0.09
     comod
    0.08
     possibility
    0.08
     berücksicht
    0.08
     berücksichtigt
    0.08
    考虑
    0.08
     ATTRIBUTE
    0.07
     betrachtet
    0.07
     고려
    0.07
    ichtigkeit
    0.07
    Activations Density 0.036%

    No Known Activations