© 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. 22616
    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
     אנחנו
    -0.10
    лім
    -0.10
     We're
    -0.10
     שאנחנו
    -0.10
     ខ
    -0.10
     ambazo
    -0.09
    、名無し
    -0.09
     кој
    -0.09
    ылатын
    -0.09
     assum
    -0.09
    POSITIVE LOGITS
     such
    0.11
    With
    0.11
    Having
    0.10
     with
    0.10
     having
    0.10
     presence
    0.10
     resulting
    0.10
    Such
    0.09
     a
    0.09
     actually
    0.09
    Activations Density 0.040%

    No Known Activations