© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 49284
    Prev
    Next
    INDEX
    Explanations

    tout

    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
     tüm
    -0.11
     সকল
    -0.10
     सभी
    -0.10
     wszystkich
    -0.10
     tutti
    -0.10
     ಎಲ್ಲಾ
    -0.09
     barcha
    -0.09
     барлық
    -0.09
     എല്ലാ
    -0.09
     সব
    -0.09
    POSITIVE LOGITS
     ciò
    0.13
     ello
    0.11
    ләй
    0.11
     aquello
    0.10
     aquel
    0.10
     simplement
    0.10
     hvad
    0.10
     agbaye
    0.10
     excepto
    0.10
     sauf
    0.10
    Activations Density 0.004%

    No Known Activations