© 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. 25271
    Prev
    Next
    INDEX
    Explanations

    almost

    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
     dyst
    -0.07
    603
    -0.07
     budding
    -0.07
    赖
    -0.07
    inn
    -0.07
     свае
    -0.07
    yer
    -0.07
     swoje
    -0.07
     predst
    -0.07
     сваю
    -0.07
    POSITIVE LOGITS
     abdomen
    0.08
     aparência
    0.08
     rije
    0.08
     abdominal
    0.08
     محسوس
    0.08
     apariencia
    0.08
    ehir
    0.08
     منزل
    0.08
     Gelände
    0.07
     intenso
    0.07
    Activations Density 0.000%

    No Known Activations