© 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. 22674
    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
     HDMI
    -0.09
     fights
    -0.08
    evice
    -0.08
    ampoline
    -0.08
    itone
    -0.08
     décr
    -0.08
     valmist
    -0.08
     conquist
    -0.08
     MIDI
    -0.08
     prépar
    -0.08
    POSITIVE LOGITS
     costos
    0.10
    成本
    0.10
     Kosten
    0.10
    Kosten
    0.10
     biaya
    0.10
    .cost
    0.10
     optimization
    0.10
     costo
    0.09
    _avg
    0.09
     القرار
    0.09
    Activations Density 0.007%

    No Known Activations