© 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 EvalsExportsAPI 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. 63869
    Prev
    Next
    INDEX
    Explanations

    correct

    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
    cean
    -0.07
     mittel
    -0.07
    Сред
    -0.07
     сред
    -0.07
     fetched
    -0.07
     charter
    -0.07
    .Program
    -0.07
     desde
    -0.07
     pensar
    -0.07
    lator
    -0.07
    POSITIVE LOGITS
     يوجد
    0.08
     leuc
    0.08
     molti
    0.07
     mendapat
    0.07
    itius
    0.07
    _ITEMS
    0.07
     lc
    0.07
     ervoor
    0.07
     prodotti
    0.07
    poz
    0.07
    Activations Density 0.007%

    No Known Activations