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. 8363
    Prev
    Next
    INDEX
    Explanations

    is

    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
    buf
    -0.08
    гот
    -0.08
     toel
    -0.08
     bigger
    -0.08
    闪
    -0.08
    variants
    -0.08
    Enchant
    -0.08
     특히
    -0.08
     variantes
    -0.07
     Marvel
    -0.07
    POSITIVE LOGITS
     imposs
    0.14
     nonexistent
    0.14
    Undefined
    0.12
    Impossible
    0.12
     impossible
    0.12
     невозможно
    0.11
     Undefined
    0.11
    不存在
    0.11
     Impossible
    0.11
     infe
    0.11
    Activations Density 0.025%

    No Known Activations