© 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. 23-RESID-POST-AA
    11. 5568
    Prev
    Next
    INDEX
    Explanations

    x

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     symbolic
    -0.08
     sate
    -0.08
     availability
    -0.08
    的数据
    -0.08
     for
    -0.08
    数
    -0.08
     numer
    -0.08
     indépend
    -0.08
     independent
    -0.08
     epochs
    -0.08
    POSITIVE LOGITS
     adicionar
    0.11
     completar
    0.11
     Completing
    0.11
     adicion
    0.11
     içine
    0.10
     rewrite
    0.10
    □
    0.10
    완
    0.10
     completing
    0.10
     grouping
    0.10
    Activations Density 0.118%

    No Known Activations