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. 45103
    Prev
    Next
    INDEX
    Explanations

    "--"

    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
     règ
    -0.08
    -important
    -0.08
     Milton
    -0.08
    íns
    -0.08
     Hef
    -0.07
    ODULE
    -0.07
    -pencil
    -0.07
     mình
    -0.07
     asters
    -0.07
    crawler
    -0.07
    POSITIVE LOGITS
     نیز
    0.09
     datap
    0.08
     കൂടി
    0.08
    รายละเอียด
    0.08
    gegevens
    0.08
     కూడ
    0.08
     roar
    0.08
     also
    0.08
     پڻ
    0.08
     picnic
    0.08
    Activations Density 0.009%

    No Known Activations