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. 76713
    Prev
    Next
    INDEX
    Explanations

    hiccups

    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
     vệ
    -0.08
    levant
    -0.07
     questioning
    -0.07
     עומ
    -0.07
     quoted
    -0.07
    unsafe
    -0.07
     Rosa
    -0.07
    -0.07
    Referenced
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     hic
    0.11
    589
    0.09
     사
    0.08
     Teller
    0.08
     Grandpa
    0.08
     thử
    0.08
     fare
    0.08
    ocket
    0.08
     �
    0.08
    'em
    0.08
    Activations Density 0.001%

    No Known Activations