© 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. 18741
    Prev
    Next
    INDEX
    Explanations

    grace/lace

    np_max-act-logits · gemini-2.0-flash
    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
    ytt
    -0.09
    yta
    -0.08
    a
    -0.08
    iyet
    -0.08
    _{\
    -0.08
    ellite
    -0.08
    _B
    -0.08
    i
    -0.07
    у
    -0.07
     dissemin
    -0.07
    POSITIVE LOGITS
     Plusieurs
    0.09
     drei
    0.09
     Zusätzlich
    0.09
     mehrere
    0.09
     Adds
    0.08
     plusieurs
    0.08
     varios
    0.08
     Moreover
    0.07
     lingkungan
    0.07
     ():
    0.07
    Activations Density 0.001%

    No Known Activations