© 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. 45418
    Prev
    Next
    INDEX
    Explanations

    Establishing a presence

    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
     проход
    -0.09
     provenant
    -0.08
     walkthrough
    -0.08
    ана
    -0.08
     provenientes
    -0.08
     Breed
    -0.07
     ένας
    -0.07
     напр
    -0.07
     Ariana
    -0.07
     pocos
    -0.07
    POSITIVE LOGITS
     рынка
    0.13
     السوق
    0.13
     рынке
    0.12
     בתחום
    0.11
     سوق
    0.11
     mercado
    0.10
     בעולם
    0.10
     rynku
    0.10
     maritime
    0.10
    市場
    0.09
    Activations Density 0.119%

    No Known Activations