© 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 EvalsExportsinterp-engineNEWAPI 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. 110994
    Prev
    Next
    INDEX
    Explanations

    detective

    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
    трым
    -0.09
     sonho
    -0.08
     girls
    -0.08
     meisjes
    -0.08
     adulthood
    -0.08
     meninas
    -0.08
    Readers
    -0.08
    واض
    -0.08
     ceilings
    -0.08
     śred
    -0.07
    POSITIVE LOGITS
     chè
    0.08
     Very
    0.08
    .V
    0.07
    ovi
    0.07
    COMPARE
    0.07
     Christopher
    0.07
     skeptical
    0.07
     Igor
    0.07
     Frankfurt
    0.07
     Viz
    0.07
    Activations Density 0.011%

    No Known Activations