© 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 EvalsExportsAPI 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. 20576
    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
     pode
    -0.09
     its
    -0.08
    -action
    -0.08
    -with
    -0.08
    -str
    -0.08
     seinen
    -0.07
     jeho
    -0.07
    ist
    -0.07
     jego
    -0.07
     njeg
    -0.07
    POSITIVE LOGITS
     enum
    0.09
     enums
    0.09
     Schweiz
    0.09
    ednesday
    0.08
     реализации
    0.08
    Enums
    0.08
    ანია
    0.08
     rétt
    0.08
    ‍ക്കാര്
    0.08
     који
    0.08
    Activations Density 0.002%

    No Known Activations