© 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. 13155
    Prev
    Next
    INDEX
    Explanations

    Sciences

    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
     السين
    -0.08
    .linalg
    -0.08
     syl
    -0.07
    078
    -0.07
     Islands
    -0.07
     ζ
    -0.07
    成年
    -0.07
     Clearly
    -0.07
    ̈
    -0.07
    _zone
    -0.07
    POSITIVE LOGITS
     portar
    0.08
    �
    0.08
     dará
    0.08
     Franse
    0.08
     Lar
    0.08
    铜
    0.08
     discret
    0.08
     šta
    0.08
     saan
    0.08
    필
    0.07
    Activations Density 0.005%

    No Known Activations