© 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. 97690
    Prev
    Next
    INDEX
    Explanations

    in

    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
     xiy
    -0.09
    ρκ
    -0.09
     knih
    -0.09
    ουν
    -0.09
     کتاب
    -0.09
    כור
    -0.08
     ఉద్య
    -0.08
     βιβ
    -0.08
     przeci
    -0.08
     langfrist
    -0.08
    POSITIVE LOGITS
     shallow
    0.11
    airt
    0.10
     एयर
    0.10
     Air
    0.10
     air
    0.10
     wat
    0.10
     airtight
    0.10
     leak
    0.09
     luft
    0.09
     Airt
    0.09
    Activations Density 0.004%

    No Known Activations