© 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. 11-RESID-POST-AA
    11. 95756
    Prev
    Next
    INDEX
    Explanations

    vitamin D

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    翼
    -0.09
     Kamp
    -0.08
    onar
    -0.08
     جاءت
    -0.08
     เจ
    -0.08
     spettac
    -0.08
    عراض
    -0.08
    izat
    -0.08
    beras
    -0.08
     Kuk
    -0.08
    POSITIVE LOGITS
     Vitamin
    0.09
    Vitamin
    0.09
     indoor
    0.08
     uptake
    0.08
     vitamin
    0.08
    COVID
    0.08
     indoors
    0.08
     COVID
    0.07
     vacancy
    0.07
    .Drop
    0.07
    Activations Density 0.004%

    No Known Activations