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. 117757
    Prev
    Next
    INDEX
    Explanations

    +

    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
    Real
    -0.08
     dificuldade
    -0.08
    reath
    -0.08
     mondial
    -0.07
    难
    -0.07
     dificultad
    -0.07
    zo
    -0.07
     Unterschiede
    -0.07
    ÑO
    -0.07
    Difficulty
    -0.07
    POSITIVE LOGITS
    wins
    0.08
     merr
    0.08
    ussing
    0.08
     warn
    0.07
     �
    0.07
    iding
    0.07
     السف
    0.07
     Locksmith
    0.07
     wins
    0.07
     lux
    0.07
    Activations Density 0.016%

    No Known Activations