© 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. 22342
    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
     Herkunft
    -0.09
     Spitze
    -0.09
     Ausstellung
    -0.08
     내려
    -0.08
    ћ
    -0.08
    unlink
    -0.08
     происх
    -0.08
    returned
    -0.08
     반환
    -0.08
     hent
    -0.08
    POSITIVE LOGITS
    able
    0.13
    ables
    0.11
    es
    0.11
    fähig
    0.10
    ed
    0.09
    /update
    0.09
    ability
    0.09
    pad
    0.09
     into
    0.09
    ing
    0.09
    Activations Density 0.018%

    No Known Activations