© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 65496
    Prev
    Next
    INDEX
    Explanations

    conversational filler words

    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
     titulaire
    -0.09
    틴
    -0.08
     foundational
    -0.08
    源码
    -0.08
     Stiftung
    -0.08
     Worldwide
    -0.08
    规模
    -0.08
    acky
    -0.08
     Patrice
    -0.08
     advising
    -0.08
    POSITIVE LOGITS
     było
    0.08
     revelation
    0.08
     habían
    0.08
     Revelation
    0.08
    айт
    0.08
     była
    0.08
     hacía
    0.08
     hadn't
    0.08
     maid
    0.08
    Recall
    0.08
    Activations Density 0.222%

    No Known Activations