© 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. 21604
    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
     পরে
    -0.09
     Subsequently
    -0.09
     এরপর
    -0.09
     subsequent
    -0.09
    järel
    -0.09
    gelopen
    -0.09
     থেক
    -0.09
     proceeded
    -0.08
     Subse
    -0.08
     তারপর
    -0.08
    POSITIVE LOGITS
     formal
    0.14
     conceptual
    0.13
     crystall
    0.12
     formulate
    0.12
    formal
    0.11
     formulated
    0.11
     Formal
    0.11
    Formal
    0.11
    正式
    0.11
     formally
    0.10
    Activations Density 0.012%

    No Known Activations