© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 16267
    Prev
    Next
    INDEX
    Explanations

    Biceps exercises

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     abge
    -0.08
    meti
    -0.08
     Kada
    -0.08
    مالي
    -0.08
    âme
    -0.07
     Gemeinden
    -0.07
    abre
    -0.07
    njo
    -0.07
    ćih
    -0.07
     komin
    -0.07
    POSITIVE LOGITS
     lure
    0.09
    Plot
    0.07
     bait
    0.07
     göre
    0.07
     TAR
    0.07
     something
    0.07
    .cmb
    0.07
     Something
    0.07
    Spline
    0.07
    _TWO
    0.07
    Activations Density 0.000%

    No Known Activations