© 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. 15-RESID-POST-AA
    11. 16437
    Prev
    Next
    INDEX
    Explanations

    gift card

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     पृथ
    -0.09
     edema
    -0.08
     Arrest
    -0.08
     древ
    -0.08
     Ancient
    -0.08
    ellipse
    -0.08
     ancient
    -0.08
     corpse
    -0.07
     obstruction
    -0.07
    ustering
    -0.07
    POSITIVE LOGITS
     vouchers
    0.12
    充值
    0.12
     Gutschein
    0.11
     cadeaux
    0.11
     Gutsche
    0.11
    额度
    0.11
     подар
    0.11
    兑换
    0.11
     cadeau
    0.10
     prepaid
    0.10
    Activations Density 0.016%

    No Known Activations