© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 19369
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Before
    -0.10
    _before
    -0.09
    _namespace
    -0.09
     ruk
    -0.09
    Before
    -0.08
     prije
    -0.08
    _POST
    -0.08
    -0.08
     before
    -0.08
    Namespace
    -0.08
    POSITIVE LOGITS
     interior
    0.19
    Interior
    0.16
     внутренних
    0.15
     Interior
    0.14
     внутрен
    0.14
     الداخلية
    0.14
     interiores
    0.14
     الداخلي
    0.14
     interiors
    0.13
     intérieur
    0.13
    Activations Density 0.012%
    No Known Activations