© 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. 21375
    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
     large
    -0.15
     높은
    -0.15
     sophisticated
    -0.15
     high
    -0.14
     큰
    -0.14
     высокого
    -0.14
     sizable
    -0.14
     высоким
    -0.13
     высок
    -0.13
     intricate
    -0.13
    POSITIVE LOGITS
    自慰
    0.09
    ervolgens
    0.09
    itening
    0.08
     kapena
    0.08
    сама
    0.08
     olemas
    0.08
    ()?
    0.08
    аще
    0.08
     ataupun
    0.08
     kumbe
    0.08
    Activations Density 0.117%

    No Known Activations