© 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. 19260
    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
     it'll
    -0.13
     olema
    -0.12
     যাবে
    -0.12
    trying
    -0.12
     It'll
    -0.12
     that'll
    -0.11
     they'll
    -0.11
     they'd
    -0.11
     inuu
    -0.10
     ताकि
    -0.10
    POSITIVE LOGITS
     notably
    0.13
     can
    0.12
    /or
    0.12
    ’s
    0.12
     function
    0.11
    ’re
    0.11
     may
    0.11
     often
    0.11
     undergo
    0.11
     frequently
    0.10
    Activations Density 0.047%

    No Known Activations