© 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. 3-RESID-POST-AA
    11. 2931
    Prev
    Next
    INDEX
    Explanations

    Give

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jak
    -0.08
     включает
    -0.08
     circumstance
    -0.08
    ябрь
    -0.08
     уб
    -0.08
     દૂર
    -0.07
     сок
    -0.07
     filmed
    -0.07
     пок
    -0.07
     nat
    -0.07
    POSITIVE LOGITS
     dv
    0.09
    Born
    0.08
    Four
    0.08
    143
    0.08
     Keen
    0.07
     frank
    0.07
    ibatkan
    0.07
    GO
    0.07
     unbiased
    0.07
     triples
    0.07
    Activations Density 0.020%

    No Known Activations