© 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. 20196
    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
     तीन
    -0.11
     three
    -0.11
     trio
    -0.11
     drie
    -0.11
     três
    -0.11
     drei
    -0.10
     három
    -0.10
     മൂന്ന്
    -0.10
     üç
    -0.10
     trois
    -0.10
    POSITIVE LOGITS
     fourth
    0.25
     fifth
    0.24
     sixth
    0.22
     seventh
    0.22
     eighth
    0.21
     quart
    0.20
     Fourth
    0.20
     Fifth
    0.19
    Fourth
    0.18
     quatrième
    0.18
    Activations Density 0.108%

    No Known Activations