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. 58379
    Prev
    Next
    INDEX
    Explanations

    disciple

    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
     بین
    -0.08
     teng
    -0.08
    岛
    -0.08
     наруж
    -0.08
     Hansen
    -0.08
     رہے
    -0.08
     تین
    -0.08
     Дан
    -0.08
     pallet
    -0.08
     Hoge
    -0.08
    POSITIVE LOGITS
     disciples
    0.10
    hip
    0.09
     devotion
    0.09
     ferv
    0.08
     fede
    0.08
     followers
    0.08
     chanting
    0.08
     Jésus
    0.08
     Jesus
    0.07
     loyal
    0.07
    Activations Density 0.008%

    No Known Activations