© 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. 19680
    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
     deres
    -0.09
     deras
    -0.09
     әск
    -0.09
     ejus
    -0.09
     қалай
    -0.09
    उन्होंने
    -0.09
    {}↵↵
    -0.09
     njihov
    -0.09
    ?.↵↵
    -0.08
     hans
    -0.08
    POSITIVE LOGITS
     usually
    0.22
     typically
    0.22
     обычно
    0.21
    Typically
    0.21
     Typically
    0.21
    usually
    0.20
     Usually
    0.20
    Usually
    0.19
     généralement
    0.19
    typically
    0.19
    Activations Density 0.063%

    No Known Activations