© 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. 3036
    Prev
    Next
    INDEX
    Explanations

    diminish

    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
     Lact
    -0.09
     Clifton
    -0.07
    告
    -0.07
     Cow
    -0.07
    .(*
    -0.07
     gating
    -0.07
    ocl
    -0.07
    ACA
    -0.07
    Oper
    -0.07
    抜
    -0.07
    POSITIVE LOGITS
    mente
    0.09
     DIM
    0.08
     വിത
    0.08
     આ
    0.07
     bezel
    0.07
     sunlight
    0.07
    -te
    0.07
     gab
    0.07
     impat
    0.07
     ئال
    0.07
    Activations Density 0.004%

    No Known Activations