© 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. 22015
    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
     Fres
    -0.10
     fresco
    -0.10
     fresca
    -0.10
     reload
    -0.08
    ுது
    -0.08
    assle
    -0.08
     ambiance
    -0.08
    ímica
    -0.08
    ógica
    -0.07
     feu
    -0.07
    POSITIVE LOGITS
     disparities
    0.35
     disparity
    0.30
     inequality
    0.29
     inequalities
    0.29
     desigual
    0.29
     unequal
    0.24
     inequ
    0.23
     uneven
    0.21
    פער
    0.20
    贫
    0.20
    Activations Density 0.047%

    No Known Activations