© 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. 23-RESID-POST-AA
    11. 49932
    Prev
    Next
    INDEX
    Explanations

    but

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     not
    -0.19
     nejen
    -0.19
     não
    -0.18
     nicht
    -0.18
    不仅
    -0.18
     tidak
    -0.17
     niet
    -0.16
     Não
    -0.16
     ikke
    -0.15
     Tidak
    -0.15
    POSITIVE LOGITS
     vielmehr
    0.24
    む
    0.13
     downright
    0.12
     degelijk
    0.11
     скорее
    0.11
     darum
    0.10
    ainkan
    0.10
     بلکه
    0.10
     eý
    0.09
     actively
    0.09
    Activations Density 0.145%

    No Known Activations