© 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. 114183
    Prev
    Next
    INDEX
    Explanations

    Javascript file processing

    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
    Distributed
    -0.08
     اليومية
    -0.07
     stresses
    -0.07
     prize
    -0.07
     spoken
    -0.07
    .daily
    -0.07
    pr
    -0.07
     സമ്മ
    -0.07
     proactive
    -0.07
     sehari
    -0.07
    POSITIVE LOGITS
    透
    0.09
     elucid
    0.08
    、电
    0.08
    cedence
    0.08
     display
    0.08
     אינ
    0.08
     Kap
    0.08
    0.08
     Fibre
    0.07
     انتهاء
    0.07
    Activations Density 0.001%
    No Known Activations