© 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. 70317
    Prev
    Next
    INDEX
    Explanations

    Rain

    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
     loj
    -0.09
     lob
    -0.08
     colo
    -0.08
     contest
    -0.08
     kritik
    -0.08
     Colo
    -0.08
     galax
    -0.08
     Rund
    -0.07
     mor
    -0.07
     Hera
    -0.07
    POSITIVE LOGITS
    adi
    0.09
     tropical
    0.09
    ADI
    0.08
    bows
    0.08
    дет
    0.08
     mol
    0.08
    fälle
    0.08
    /fire
    0.07
    শ
    0.07
    water
    0.07
    Activations Density 0.008%

    No Known Activations