© 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. 20747
    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
    level
    -0.09
    ท้าย
    -0.09
    commit
    -0.08
     さん
    -0.08
     trois
    -0.08
     commit
    -0.08
     trzy
    -0.08
     relocate
    -0.07
    transfer
    -0.07
     alphabetical
    -0.07
    POSITIVE LOGITS
     perpendicular
    0.18
     lengths
    0.14
    _lengths
    0.12
    Lengths
    0.12
     diagon
    0.11
     axes
    0.11
    尺寸
    0.11
     comprimento
    0.11
     halves
    0.11
    _angles
    0.11
    Activations Density 0.020%

    No Known Activations