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. 65671
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Wissen
    -0.08
     conocimiento
    -0.08
     '../../../
    -0.08
     "../../../
    -0.08
     Compose
    -0.07
     "../
    -0.07
     فضل
    -0.07
    енье
    -0.07
     Fondo
    -0.07
     skupaj
    -0.07
    POSITIVE LOGITS
     →
    0.08
    👉
    0.08
    .put
    0.07
     genomes
    0.07
     enda
    0.07
    ibbon
    0.07
    _shadow
    0.07
    .jvm
    0.07
    .Program
    0.07
     homeland
    0.07
    Activations Density 0.000%

    No Known Activations