© 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. 23-RESID-POST-AA
    11. 52205
    Prev
    Next
    INDEX
    Explanations

    Trigonometric sine functions

    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
    Negative Logits
    nef
    -0.08
    odis
    -0.08
     conscious
    -0.08
    akel
    -0.07
     glossy
    -0.07
    .abspath
    -0.07
    _dis
    -0.07
     Тел
    -0.07
    #ab
    -0.07
     nef
    -0.07
    POSITIVE LOGITS
     sin
    0.15
     identities
    0.15
     sine
    0.15
     trigo
    0.14
    sin
    0.13
     cosine
    0.13
     sins
    0.13
    sins
    0.13
     identity
    0.12
     radians
    0.12
    Activations Density 0.071%

    No Known Activations