© 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. 7-RESID-POST-AA
    11. 1389
    Prev
    Next
    INDEX
    Explanations

    senior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nonce
    -0.08
     Necess
    -0.08
     tran
    -0.07
     nicotine
    -0.07
     потреб
    -0.07
     повод
    -0.07
    224
    -0.07
     dirt
    -0.07
     �
    -0.07
     leftover
    -0.07
    POSITIVE LOGITS
     �
    0.09
    樓
    0.08
     tuổi
    0.08
     Soh
    0.08
    彩票
    0.07
    楼
    0.07
    望
    0.07
     osteoporosis
    0.07
     جداً
    0.07
    יכר
    0.07
    Activations Density 0.011%

    No Known Activations