© 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. 22475
    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
    ционной
    -0.09
    циях
    -0.09
     Carmel
    -0.09
    ೇಶ
    -0.09
    േഷന്
    -0.08
    ATION
    -0.08
    ционная
    -0.08
     llevará
    -0.08
    цыі
    -0.08
    цый
    -0.08
    POSITIVE LOGITS
    neider
    0.17
    leswig
    0.16
    midt
    0.15
    lüss
    0.15
    reibt
    0.15
    umacher
    0.15
    ätzung
    0.15
    lüssel
    0.14
    reiber
    0.14
    affung
    0.14
    Activations Density 0.022%

    No Known Activations