© 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. 63773
    Prev
    Next
    INDEX
    Explanations

    Conditional statements

    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
     nejen
    -0.08
    ianos
    -0.08
     parle
    -0.08
     speeches
    -0.08
    车型
    -0.08
     ferry
    -0.07
     hurricanes
    -0.07
    peech
    -0.07
     riots
    -0.07
    eyen
    -0.07
    POSITIVE LOGITS
     necessarily
    0.09
    -д
    0.08
     八
    0.08
    ardan
    0.08
     Aspir
    0.07
    む
    0.07
    ا
    0.07
     deren
    0.07
    八
    0.07
     ones
    0.07
    Activations Density 0.118%

    No Known Activations