© 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. 7-RESID-POST-AA
    11. 996
    Prev
    Next
    INDEX
    Explanations

    parameters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dispose
    -0.08
     talks
    -0.07
     MEC
    -0.07
    Talk
    -0.07
    できます
    -0.07
     he's
    -0.07
    psy
    -0.07
    _mp
    -0.07
    రవ
    -0.07
    ঠন
    -0.07
    POSITIVE LOGITS
     verla
    0.08
    .opend
    0.08
     Öğ
    0.07
     Richardson
    0.07
     ars
    0.07
     Griffith
    0.07
     Una
    0.07
     verhind
    0.07
     verfüg
    0.07
    una
    0.07
    Activations Density 0.001%

    No Known Activations