© 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. 3-RESID-POST-AA
    11. 13332
    Prev
    Next
    INDEX
    Explanations

    .After

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Srb
    -0.09
    DU
    -0.08
     ake
    -0.08
    -0.08
     Sar
    -0.07
     DU
    -0.07
    Bust
    -0.07
     Siv
    -0.07
     gå
    -0.07
     needed
    -0.07
    POSITIVE LOGITS
    273
    0.08
    żeli
    0.08
     Presents
    0.08
     magnesium
    0.08
     consta
    0.08
    325
    0.08
    skal
    0.08
    ন্ত্রণ
    0.07
     Present
    0.07
    groep
    0.07
    Activations Density 0.001%
    No Known Activations