© 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. 15-RESID-POST-AA
    11. 16616
    Prev
    Next
    INDEX
    Explanations

    Numbered lists

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -than
    -0.08
    -have
    -0.08
    -wow
    -0.08
     zároveň
    -0.08
    (reverse
    -0.07
    295
    -0.07
     ايضا
    -0.07
    verted
    -0.07
    also
    -0.07
     maneuver
    -0.07
    POSITIVE LOGITS
     Juda
    0.08
    .check
    0.08
     Defesa
    0.08
     igre
    0.07
    тыра
    0.07
    .JSONArray
    0.07
    াস্থ্য
    0.07
     Saúde
    0.07
    Bref
    0.07
     JCheck
    0.07
    Activations Density 0.010%

    No Known Activations