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. 101700
    Prev
    Next
    INDEX
    Explanations

    company events and office

    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
     unfor
    -0.07
    oreg
    -0.07
     Apple's
    -0.07
    _real
    -0.07
    صول
    -0.07
    .Normalize
    -0.07
    .Distance
    -0.07
     cif
    -0.07
    _max
    -0.07
    _loss
    -0.07
    POSITIVE LOGITS
     celebrating
    0.12
     anniversary
    0.12
     celebrate
    0.11
     celebration
    0.11
    Subscribers
    0.10
    庆
    0.10
    members
    0.10
    employees
    0.10
    Celebrate
    0.10
    周年
    0.10
    Activations Density 0.149%

    No Known Activations