© 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. 19-RESID-POST-AA
    11. 18159
    Prev
    Next
    INDEX
    Explanations

    trigonometry

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     philanth
    -0.09
     વાર
    -0.09
     geboorte
    -0.09
     જન્મ
    -0.08
    -custom
    -0.08
    注册送
    -0.08
     centralized
    -0.08
    三区
    -0.08
     million
    -0.08
     Geburt
    -0.08
    POSITIVE LOGITS
     cosine
    0.16
     perpendicular
    0.16
    *cos
    0.15
    *sin
    0.15
     cos
    0.14
     √
    0.14
    √
    0.13
     sine
    0.13
     sqrt
    0.13
     sin
    0.13
    Activations Density 0.025%

    No Known Activations