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. 117499
    Prev
    Next
    INDEX
    Explanations

    Song

    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
    flammatory
    -0.08
     MW
    -0.08
    MW
    -0.08
     acidente
    -0.08
     reusable
    -0.08
    ljuč
    -0.08
    वाही
    -0.08
    ostí
    -0.08
     uncert
    -0.08
    acce
    -0.08
    POSITIVE LOGITS
    -era
    0.10
     era
    0.09
    宋
    0.09
    Era
    0.08
    时期
    0.08
     dynasty
    0.08
    Din
    0.08
    江
    0.07
     Kam
    0.07
     civilization
    0.07
    Activations Density 0.005%

    No Known Activations