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. 58098
    Prev
    Next
    INDEX
    Explanations

    the

    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
     можуть
    -0.08
    須
    -0.07
    Guru
    -0.07
    Prefs
    -0.07
     revolution
    -0.07
    VO
    -0.07
    随后
    -0.07
     Hol
    -0.07
    ’র
    -0.07
     начинают
    -0.07
    POSITIVE LOGITS
     razon
    0.08
     racional
    0.07
     altitude
    0.07
     комбина
    0.07
     Edith
    0.07
     broj
    0.07
    Intersection
    0.07
    рани
    0.07
     difference
    0.07
    ది
    0.07
    Activations Density 0.094%

    No Known Activations