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. 30799
    Prev
    Next
    INDEX
    Explanations

    accommodating capacity

    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
     directly
    -0.07
     conditional
    -0.07
     preference
    -0.07
     common
    -0.07
     préférence
    -0.07
    Conditional
    -0.07
     Bob
    -0.06
     selecting
    -0.06
     Swagger
    -0.06
     table
    -0.06
    POSITIVE LOGITS
     capaciteit
    0.20
    _capacity
    0.17
     kapas
    0.17
    capacity
    0.16
    Capacity
    0.16
     Capacity
    0.16
     capacity
    0.16
    容量
    0.16
     ظرفیت
    0.16
    .capacity
    0.15
    Activations Density 0.097%

    No Known Activations