© 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. 110448
    Prev
    Next
    INDEX
    Explanations

    vials

    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
     한번
    -0.09
    laget
    -0.08
    aringan
    -0.08
    报
    -0.07
     joining
    -0.07
    乎
    -0.07
     joins
    -0.07
     nav
    -0.07
     ವಿಮ
    -0.07
    -padding
    -0.07
    POSITIVE LOGITS
     precar
    0.09
     Note
    0.08
    (Blueprint
    0.08
     documented
    0.08
     دوا
    0.08
     المخت
    0.08
     Experiment
    0.08
     perfume
    0.08
     pharm
    0.07
     depict
    0.07
    Activations Density 0.009%

    No Known Activations