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. 45192
    Prev
    Next
    INDEX
    Explanations

    communication

    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
     Nichols
    -0.08
    (土
    -0.08
     구축
    -0.07
    中新
    -0.07
     MSS
    -0.07
     spool
    -0.07
     Km
    -0.07
     Ley
    -0.07
     базы
    -0.07
     backbone
    -0.07
    POSITIVE LOGITS
     joker
    0.08
    /email
    0.08
    🏻
    0.08
    🏼
    0.07
     dart
    0.07
     Hamlet
    0.07
     Rok
    0.07
     nick
    0.07
    Joel
    0.07
    joker
    0.07
    Activations Density 38.519%

    No Known Activations