© 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. 11-RESID-POST-AA
    11. 75500
    Prev
    Next
    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uncover
    -0.08
     침
    -0.08
     vacc
    -0.07
     conducir
    -0.07
     moistur
    -0.07
     خون
    -0.07
     microorganisms
    -0.07
    .autocon
    -0.07
     Fernando
    -0.07
     hoeveelheid
    -0.07
    POSITIVE LOGITS
     nonlinear
    0.09
     Like
    0.08
     retains
    0.08
     Instead
    0.07
    ഴ
    0.07
     thể
    0.07
    יזם
    0.07
     Unlike
    0.07
     строк
    0.07
     Iterate
    0.07
    Activations Density 0.079%

    No Known Activations