© 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 EvalsExportsAPI 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. 20155
    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
    :param
    -0.10
    :get
    -0.09
    :function
    -0.09
    =http
    -0.09
    feest
    -0.09
    \web
    -0.09
    _dataframe
    -0.09
     funzione
    -0.09
    @param
    -0.08
    érie
    -0.08
    POSITIVE LOGITS
     Whether
    0.10
     برامج
    0.09
     It
    0.09
     Other
    0.09
     Its
    0.08
     ẹ
    0.08
     Ён
    0.08
     Written
    0.08
     Others
    0.08
     Õ
    0.08
    Activations Density 0.002%

    No Known Activations