© 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. 113715
    Prev
    Next
    INDEX
    Explanations

    Americas countries

    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
     chví
    -0.09
    CHED
    -0.08
    181
    -0.08
    156
    -0.08
    159
    -0.08
     raz
    -0.08
    ste
    -0.07
    182
    -0.07
    bein
    -0.07
     ancestral
    -0.07
    POSITIVE LOGITS
     slang
    0.09
     Helpful
    0.08
     úteis
    0.08
     studi
    0.08
     throughout
    0.08
     ಉಪ
    0.08
     entertaining
    0.08
     разговор
    0.08
     synonyms
    0.07
     helpful
    0.07
    Activations Density 0.005%

    No Known Activations