© 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. 111306
    Prev
    Next
    INDEX
    Explanations

    gallons

    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
     Mer
    -0.08
    nde
    -0.07
    've
    -0.07
    ikot
    -0.07
    ปร
    -0.07
    eri
    -0.07
     carcin
    -0.07
     kai
    -0.07
    lk
    -0.07
     ധ
    -0.07
    POSITIVE LOGITS
    zahlen
    0.09
    Interp
    0.08
     топлива
    0.08
    rise
    0.08
    _interp
    0.07
    interp
    0.07
     증가
    0.07
    -ft
    0.07
    NV
    0.07
     Dise
    0.07
    Activations Density 0.005%

    No Known Activations