© 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. 94524
    Prev
    Next
    INDEX
    Explanations

    2

    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
     Iv
    -0.08
    dark
    -0.07
     Singles
    -0.07
     mbi
    -0.07
    mi
    -0.07
     Drama
    -0.07
    IGE
    -0.07
    tren
    -0.07
    visited
    -0.07
    াঙ
    -0.07
    POSITIVE LOGITS
    在人
    0.08
     структ
    0.08
     politiques
    0.08
     انس
    0.07
    [email
    0.07
     políticas
    0.07
    Dans
    0.07
    -human
    0.07
     puissant
    0.07
     tejido
    0.07
    Activations Density 0.001%

    No Known Activations