© 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. 70060
    Prev
    Next
    INDEX
    Explanations

    Code, math, foreign languages

    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
     affront
    -0.08
     x
    -0.07
     Tengo
    -0.07
    “My
    -0.07
    _element
    -0.07
     scrum
    -0.07
    _sched
    -0.07
     Vai
    -0.07
     illustrative
    -0.07
    あります
    -0.07
    POSITIVE LOGITS
    teilungen
    0.08
     delen
    0.07
    Pivot
    0.07
     nar
    0.07
     Pivot
    0.07
     Moll
    0.07
    pager
    0.07
    }-{
    0.07
    ‌,
    0.07
     그러나
    0.07
    Activations Density 0.000%

    No Known Activations