© 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. 70664
    Prev
    Next
    INDEX
    Explanations

    actor

    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
     loin
    -0.08
     divertir
    -0.08
     ahi
    -0.07
     hacks
    -0.07
     gré
    -0.07
    नेट
    -0.07
     ಮಾಡ
    -0.07
     Yale
    -0.07
     insan
    -0.07
     hie
    -0.07
    POSITIVE LOGITS
    棋
    0.10
     בתחום
    0.09
     рынка
    0.09
     рынке
    0.08
     Zhang
    0.08
     Λ
    0.08
    acters
    0.08
    Lambda
    0.08
     locus
    0.08
     partijen
    0.08
    Activations Density 0.028%

    No Known Activations