© 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. 64843
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     LAN
    -0.08
     PREC
    -0.08
    ান্ত
    -0.08
     dicas
    -0.08
    tyw
    -0.08
    리에
    -0.08
    -0.08
    DDL
    -0.08
    aneously
    -0.07
    ಕ್ಕೆ
    -0.07
    POSITIVE LOGITS
     jean
    0.08
    杰
    0.08
     tout
    0.08
     Morgan
    0.08
    yaa
    0.07
     bold
    0.07
     financières
    0.07
     oscur
    0.07
     기자
    0.07
     JSImport
    0.07
    Activations Density 0.011%
    No Known Activations