Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 77249
    Prev
    Next
    INDEX
    Explanations

    Reheating food with liquid

    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
    /control
    -0.07
     brav
    -0.07
    nas
    -0.07
    enção
    -0.07
     hdr
    -0.07
    -sac
    -0.07
    دع
    -0.07
    engo
    -0.07
    هاب
    -0.07
     haar
    -0.07
    POSITIVE LOGITS
     reinst
    0.11
    重新
    0.11
    再次
    0.10
     yeniden
    0.10
     rebuilding
    0.10
     ફરી
    0.10
     വീണ്ടും
    0.09
    _restore
    0.09
     ગર
    0.09
     reprendre
    0.09
    Activations Density 0.002%

    No Known Activations