© 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. 21697
    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
     intermediate
    -0.10
     both
    -0.10
     adjacent
    -0.09
     interim
    -0.09
     ಮಧ್ಯ
    -0.08
     મધ
    -0.08
     ambos
    -0.08
    Intermediate
    -0.08
     मध
    -0.08
     zowel
    -0.08
    POSITIVE LOGITS
     Highest
    0.16
     highest
    0.15
    Highest
    0.14
    highest
    0.13
     нај
    0.13
    最高
    0.13
     najwy
    0.12
     ഏറ്റവും
    0.12
     najwięks
    0.12
     સૌથી
    0.12
    Activations Density 0.049%

    No Known Activations