© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 63786
    Prev
    Next
    INDEX
    Explanations

    negations and justifications

    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
     afinal
    -0.09
     הרי
    -0.08
     TAL
    -0.08
     considerar
    -0.08
     Fahrenheit
    -0.08
     Afinal
    -0.08
     hés
    -0.07
     dale
    -0.07
     Hick
    -0.07
     zarówno
    -0.07
    POSITIVE LOGITS
     veneer
    0.09
    -suite
    0.08
     delayed
    0.08
     conveniente
    0.08
    -le
    0.08
    -style
    0.08
     приятно
    0.08
    -type
    0.07
    ueling
    0.07
     cole
    0.07
    Activations Density 0.094%

    No Known Activations