© 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. 19862
    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
     considered
    -0.09
     regarded
    -0.08
     माना
    -0.08
     toto
    -0.08
     ایک
    -0.07
     dlo
    -0.07
    (dtype
    -0.07
    =models
    -0.07
     etdi
    -0.07
     desfile
    -0.07
    POSITIVE LOGITS
    _between
    0.11
    Between
    0.10
     Between
    0.09
    _angle
    0.09
    etween
    0.09
    between
    0.09
     来
    0.08
    Radians
    0.08
    _angles
    0.08
    -between
    0.08
    Activations Density 0.011%

    No Known Activations