© 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. 3-RESID-POST-AA
    11. 1127
    Prev
    Next
    INDEX
    Explanations

    aid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     зан
    -0.08
     distribu
    -0.08
    ーズ
    -0.08
    ನ್ನು
    -0.08
    ্জ
    -0.07
    fjord
    -0.07
     clinically
    -0.07
     afecta
    -0.07
     hidrat
    -0.07
    _EX
    -0.07
    POSITIVE LOGITS
    ARO
    0.08
     Kane
    0.07
     Norris
    0.07
     ry
    0.07
     usefulness
    0.07
    raj
    0.07
     aile
    0.07
    .owner
    0.07
     cryptocurrencies
    0.07
     Roy
    0.07
    Activations Density 0.001%

    No Known Activations