© 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. 11-RESID-POST-AA
    11. 30425
    Prev
    Next
    INDEX
    Explanations

    mod

    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
     collective
    -0.08
    ueless
    -0.07
    વાનો
    -0.07
    collect
    -0.07
     cursed
    -0.07
     કરવાનો
    -0.07
     collectively
    -0.07
    estima
    -0.07
    .Department
    -0.07
     toplam
    -0.07
    POSITIVE LOGITS
     wiederum
    0.09
     снова
    0.09
     שוב
    0.08
     erneut
    0.08
     nuevamente
    0.08
     naman
    0.08
     Gabriel
    0.08
     هل
    0.08
     desal
    0.08
     maneh
    0.08
    Activations Density 0.018%

    No Known Activations