© 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. 31258
    Prev
    Next
    INDEX
    Explanations

    Outlook

    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
    転
    -0.08
    behind
    -0.08
    နိုင်
    -0.08
     tunnel
    -0.07
     LGBT
    -0.07
     لین
    -0.07
    ündet
    -0.07
     rin
    -0.07
    porn
    -0.07
    ünden
    -0.07
    POSITIVE LOGITS
    혈
    0.08
     clín
    0.08
     Bon
    0.08
     correo
    0.08
     productividad
    0.08
    /calendar
    0.08
    병
    0.08
    mos
    0.07
     Joaquin
    0.07
    .exe
    0.07
    Activations Density 0.003%

    No Known Activations