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. 65255
    Prev
    Next
    INDEX
    Explanations

    single

    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
    attach
    -0.08
    coe
    -0.08
     attach
    -0.08
     attaching
    -0.07
     examine
    -0.07
    ka
    -0.07
    Nam
    -0.07
    _(
    -0.07
     identity
    -0.07
     transcription
    -0.07
    POSITIVE LOGITS
     mõju
    0.09
     slab
    0.09
    яса
    0.09
     хоҳад
    0.09
     kura
    0.09
     бошад
    0.09
     чай
    0.08
    ошта
    0.08
    (cols
    0.08
    .Sensor
    0.08
    Activations Density 0.003%

    No Known Activations