© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 111420
    Prev
    Next
    INDEX
    Explanations

    approximate

    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
     namens
    -0.08
     Lula
    -0.08
     Dolph
    -0.08
     대신
    -0.08
     schein
    -0.07
     �
    -0.07
    clazz
    -0.07
     Angelo
    -0.07
    Apellido
    -0.07
     eduk
    -0.07
    POSITIVE LOGITS
    imate
    0.08
     mener
    0.07
     vantage
    0.07
     proto
    0.07
    程度
    0.07
     conductivity
    0.07
    endet
    0.07
    路线
    0.07
     footh
    0.07
     localização
    0.07
    Activations Density 0.008%

    No Known Activations