© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1440
    Prev
    Next
    INDEX
    Explanations

    area between graph and x-axis

    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
     prove
    -0.08
     Pé
    -0.08
     Erl
    -0.08
     tomb
    -0.08
    Rs
    -0.07
     ridd
    -0.07
    inte
    -0.07
    性生活
    -0.07
    مة
    -0.07
     proving
    -0.07
    POSITIVE LOGITS
    .plot
    0.09
     seab
    0.09
     plotted
    0.09
     sinus
    0.09
     sinu
    0.08
    走势
    0.08
     shading
    0.08
     çiz
    0.08
    坂
    0.08
    Contours
    0.08
    Activations Density 0.027%

    No Known Activations