© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 71486
    Prev
    Next
    INDEX
    Explanations

    improvements and capabilities

    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
    仔
    -0.09
     vaguely
    -0.08
    接受
    -0.08
    爰
    -0.07
     algún
    -0.07
    lj
    -0.07
     Sonia
    -0.07
    lament
    -0.07
    urther
    -0.07
     örg
    -0.07
    POSITIVE LOGITS
     doordat
    0.12
     dankzij
    0.11
     unprecedented
    0.10
     Enables
    0.10
     graças
    0.10
     effortlessly
    0.09
     मिनट
    0.09
     быстрее
    0.09
     empowers
    0.09
    Grâce
    0.09
    Activations Density 0.213%

    No Known Activations