© 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. 19-RESID-POST-AA
    11. 103623
    Prev
    Next
    INDEX
    Explanations

    determine

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gerechnet
    -0.08
     lema
    -0.07
     embrace
    -0.07
     Encour
    -0.07
     erhö
    -0.07
     عباس
    -0.07
    -0.07
    сенді
    -0.07
     rising
    -0.07
     скачать
    -0.07
    POSITIVE LOGITS
     déterminer
    0.33
     determinar
    0.32
     determining
    0.32
    Determ
    0.31
    Determine
    0.30
     Determine
    0.30
     determine
    0.30
     bepalen
    0.29
     determines
    0.29
     menentukan
    0.28
    Activations Density 0.230%
    No Known Activations