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. 59125
    Prev
    Next
    INDEX
    Explanations

    magnetic

    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
    ראות
    -0.08
    _Insert
    -0.08
    ומרים
    -0.08
    illä
    -0.08
    ’appro
    -0.08
    .spring
    -0.08
    /y
    -0.08
    ’informations
    -0.07
    _files
    -0.07
     weiteren
    -0.07
    POSITIVE LOGITS
     protective
    0.10
     geom
    0.08
     Protective
    0.08
     beneficial
    0.08
     Öffentlich
    0.08
     Z
    0.08
    堡
    0.07
     child's
    0.07
     børn
    0.07
     att
    0.07
    Activations Density 0.002%

    No Known Activations