© 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. 17945
    Prev
    Next
    INDEX
    Explanations

    subclasses and inheritance

    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
     averaged
    -0.08
    умен
    -0.07
     tổng
    -0.07
     repeated
    -0.07
     central
    -0.07
     συνο
    -0.07
     okvir
    -0.07
     pozw
    -0.07
     tổ
    -0.07
    _ori
    -0.07
    POSITIVE LOGITS
     subclass
    0.34
     subclasses
    0.32
    Subclass
    0.27
     inherits
    0.25
     наслед
    0.25
    继
    0.25
     inher
    0.24
     inherit
    0.23
     subtype
    0.23
    inherits
    0.23
    Activations Density 0.014%

    No Known Activations