© 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. 11-RESID-POST-AA
    11. 47398
    Prev
    Next
    INDEX
    Explanations

    reverse engineering software

    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
    axe
    -0.08
     তুল
    -0.08
     peda
    -0.07
    aryl
    -0.07
     habla
    -0.07
    .operator
    -0.07
     bygg
    -0.07
     Handling
    -0.07
    achtige
    -0.07
     etwa
    -0.07
    POSITIVE LOGITS
     FBI
    0.09
    ваюць
    0.08
    тие
    0.07
     vort
    0.07
     campeonato
    0.07
     cold
    0.07
     expand
    0.07
    sten
    0.07
     warming
    0.07
    uuid
    0.07
    Activations Density 0.000%

    No Known Activations