© 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. 70027
    Prev
    Next
    INDEX
    Explanations

    reviews

    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
     Styling
    -0.08
    jekte
    -0.08
     Sty
    -0.08
     malade
    -0.08
     feest
    -0.08
     kug
    -0.08
     Kort
    -0.07
    >::
    -0.07
     jedna
    -0.07
     zd
    -0.07
    POSITIVE LOGITS
     corrobor
    0.09
     unhappy
    0.08
    罗斯
    0.08
    ूत
    0.08
    avorable
    0.07
     terrible
    0.07
     негатив
    0.07
     председ
    0.07
     довольно
    0.07
     Wolver
    0.07
    Activations Density 0.060%

    No Known Activations