© 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 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. 69337
    Prev
    Next
    INDEX
    Explanations

    identical twins

    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
     announces
    -0.08
     мол
    -0.08
    _ft
    -0.07
    ого
    -0.07
    ונ
    -0.07
     proposes
    -0.07
    (named
    -0.07
     prosecutors
    -0.07
    apen
    -0.07
    lagen
    -0.07
    POSITIVE LOGITS
     chiffon
    0.09
     kiosk
    0.09
    ës
    0.08
     zee
    0.08
     EE
    0.08
     stik
    0.07
    真假
    0.07
    EE
    0.07
     குழந்த
    0.07
     indo
    0.07
    Activations Density 0.001%

    No Known Activations