© 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. 95707
    Prev
    Next
    INDEX
    Explanations

    the

    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
    sanitize
    -0.08
     zabez
    -0.07
     reconstruct
    -0.07
     masu
    -0.07
    EFI
    -0.07
     disfr
    -0.07
     wholesome
    -0.07
    .Connection
    -0.07
    >Name
    -0.07
    λύ
    -0.07
    POSITIVE LOGITS
     relent
    0.09
     Roof
    0.08
     beginnen
    0.08
    回应
    0.08
     فج
    0.08
    елек
    0.08
    ющей
    0.07
     свидетель
    0.07
     تحت
    0.07
     Rece
    0.07
    Activations Density 0.002%

    No Known Activations