© 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. 23-RESID-POST-AA
    11. 50799
    Prev
    Next
    INDEX
    Explanations

    Tungsten

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ેગ
    -0.08
    ેજ
    -0.08
    e
    -0.08
    ժ
    -0.08
    zont
    -0.08
    േജ്
    -0.08
    žje
    -0.08
    /time
    -0.08
    ्ज
    -0.07
     salut
    -0.07
    POSITIVE LOGITS
    amacare
    0.10
    arian
    0.09
    igenous
    0.09
     İlk
    0.09
    igkeit
    0.09
    arians
    0.09
     социал
    0.08
    kä
    0.08
    ible
    0.08
    inish
    0.08
    Activations Density 0.005%

    No Known Activations