© 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. 19590
    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
    _OVERRIDE
    -0.08
    -generated
    -0.08
    造成
    -0.08
    _generated
    -0.08
     naturelle
    -0.08
    _override
    -0.08
    ifax
    -0.08
    _if
    -0.08
    worthy
    -0.08
    _bias
    -0.08
    POSITIVE LOGITS
     increased
    0.11
     higher
    0.11
     years
    0.10
     intensive
    0.10
     extensive
    0.10
     high
    0.10
     engagement
    0.10
     participation
    0.09
     उच्च
    0.09
     prolonged
    0.09
    Activations Density 0.010%

    No Known Activations