© 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. 111479
    Prev
    Next
    INDEX
    Explanations

    other

    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
     budget
    -0.08
     budgets
    -0.08
     hassles
    -0.08
    预算
    -0.07
    ubu
    -0.07
    SEO
    -0.07
     favoritas
    -0.07
     বাজ
    -0.07
    .",↵
    -0.07
    Budget
    -0.07
    POSITIVE LOGITS
     लगे
    0.09
    ्झ
    0.09
    .inf
    0.09
     nữa
    0.09
     Hen
    0.08
     Carl
    0.08
     कार
    0.08
     collided
    0.08
     נוסף
    0.08
    _collision
    0.08
    Activations Density 0.030%

    No Known Activations