© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68041
    Prev
    Next
    INDEX
    Explanations

    or

    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
    Ch
    -0.08
    もちろん
    -0.07
    .text
    -0.07
    Similar
    -0.07
     perennial
    -0.07
     electrolyte
    -0.07
    961
    -0.07
    राज
    -0.07
    -0.07
    કા
    -0.07
    POSITIVE LOGITS
     Hawai
    0.08
     Kidd
    0.08
     med
    0.08
     ena
    0.08
    庆
    0.08
     cient
    0.07
     aside
    0.07
     maravil
    0.07
     эти
    0.07
     какая
    0.07
    Activations Density 0.045%

    No Known Activations