© 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. 20224
    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
    Duty
    -0.09
    ：http
    -0.08
     manuals
    -0.08
    Он
    -0.08
     erad
    -0.08
     aviation
    -0.08
    Volks
    -0.08
     individual
    -0.07
    Газ
    -0.07
     asphalt
    -0.07
    POSITIVE LOGITS
    cdnjs
    0.23
    cdn
    0.16
    .jsdelivr
    0.15
    code
    0.13
    stackpath
    0.12
    libs
    0.11
    via
    0.10
    also
    0.10
     همین
    0.09
     code
    0.09
    Activations Density 0.001%

    No Known Activations