© 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. 6575
    Prev
    Next
    INDEX
    Explanations

    Time of day/week

    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
     nuanced
    -0.13
     inherent
    -0.12
     तत्व
    -0.11
     व्यापक
    -0.11
     உருவ
    -0.11
     वैश
    -0.11
     सार्व
    -0.11
     عناصر
    -0.11
     factual
    -0.11
     субъ
    -0.11
    POSITIVE LOGITS
     dinner
    0.24
     lunch
    0.21
     शनिवार
    0.21
     শনিবার
    0.21
     vacation
    0.20
     breakfast
    0.20
     birthday
    0.20
     saturday
    0.20
    Dinner
    0.19
     weekend
    0.19
    Activations Density 0.332%

    No Known Activations