© 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. 44484
    Prev
    Next
    INDEX
    Explanations

    Odin

    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
    味
    -0.08
    izations
    -0.08
    玲
    -0.08
     먼
    -0.08
     gr
    -0.08
    <Car
    -0.08
    (pi
    -0.07
     taste
    -0.07
    Grammar
    -0.07
    "})
    -0.07
    POSITIVE LOGITS
     mentre
    0.08
     कैसे
    0.08
     Quanto
    0.08
     NSA
    0.07
     enquanto
    0.07
    0.07
     dossier
    0.07
     espace
    0.07
     kuidas
    0.07
     dossiers
    0.07
    Activations Density 0.001%
    No Known Activations