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. 77541
    Prev
    Next
    INDEX
    Explanations

    special characters

    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
     disciplinas
    -0.08
     estaciones
    -0.08
    ilar
    -0.07
    journ
    -0.07
     carreras
    -0.07
     povos
    -0.07
     Corse
    -0.07
    पालिक
    -0.07
     dok
    -0.07
     проекта
    -0.07
    POSITIVE LOGITS
    054
    0.09
     تحديد
    0.08
    051
    0.08
    =%
    0.08
     bombs
    0.07
    Epic
    0.07
     belts
    0.07
    Harness
    0.07
     لر
    0.07
    .gov
    0.07
    Activations Density 0.002%

    No Known Activations