© 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. 19432
    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
     ließ
    -0.10
     khiến
    -0.09
     hästi
    -0.09
     போன்ற
    -0.09
     τόσο
    -0.09
     terminó
    -0.09
    같
    -0.09
    봤
    -0.09
     그런데
    -0.09
     इतना
    -0.08
    POSITIVE LOGITS
     receive
    0.17
     receives
    0.16
     undergo
    0.15
     encouraged
    0.15
     recebem
    0.15
    .receive
    0.15
    被
    0.15
     tasked
    0.14
     instructed
    0.14
     receber
    0.14
    Activations Density 0.061%

    No Known Activations