Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 49181
    Prev
    Next
    INDEX
    Explanations

    per

    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
     upsetting
    -0.08
     cam
    -0.07
    Мар
    -0.07
    sb
    -0.07
     notar
    -0.07
     supp
    -0.07
     উচিত
    -0.07
    cross
    -0.07
     implying
    -0.07
    ند
    -0.07
    POSITIVE LOGITS
     capita
    0.10
     Leg
    0.08
     homme
    0.08
     વખતે
    0.08
    pared
    0.08
     Lisa
    0.08
     Emil
    0.07
     Jacobs
    0.07
    pendicular
    0.07
     vind
    0.07
    Activations Density 0.040%

    No Known Activations