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. 12476
    Prev
    Next
    INDEX
    Explanations

    animal tracking

    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
     healthcare
    -0.09
     executives
    -0.09
     vocational
    -0.09
     industriais
    -0.09
     Healthcare
    -0.09
     metro
    -0.09
     industrial
    -0.09
     vendors
    -0.08
    Healthcare
    -0.08
    $str
    -0.08
    POSITIVE LOGITS
     predator
    0.13
    Species
    0.12
     Predator
    0.12
    _species
    0.12
    Animal
    0.12
     pher
    0.12
     habitat
    0.12
     habitu
    0.11
    动物
    0.11
     mating
    0.11
    Activations Density 0.023%

    No Known Activations