© 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. 22325
    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
    ，他
    -0.08
    ，那么
    -0.08
    的时候
    -0.08
    -color
    -0.08
    ，如果
    -0.07
     વખતે
    -0.07
     થી
    -0.07
     camb
    -0.07
     સમયે
    -0.07
    .watch
    -0.07
    POSITIVE LOGITS
    ώνει
    0.11
    яўляецца
    0.09
     Verkä
    0.09
    ίζει
    0.09
     their
    0.09
    ’any
    0.09
     Their
    0.09
    ہے
    0.09
    ňuje
    0.08
    ňe
    0.08
    Activations Density 0.019%

    No Known Activations