Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 23746
    Prev
    Next
    INDEX
    Explanations

    Political affiliation (R or 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
     sufic
    -0.08
    uktur
    -0.08
    ély
    -0.07
     abiding
    -0.07
     cercana
    -0.07
    -0.07
    िरी
    -0.07
     hearty
    -0.07
    zett
    -0.07
     giác
    -0.07
    POSITIVE LOGITS
    수
    0.08
     flam
    0.08
    Ac
    0.08
     сайта
    0.07
     сайте
    0.07
     dragon
    0.07
    וני
    0.07
     Congressional
    0.07
     يع
    0.07
    Au
    0.07
    Activations Density 0.006%

    No Known Activations