© 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. 75546
    Prev
    Next
    INDEX
    Explanations

    cunning

    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
    액
    -0.08
     Auditorium
    -0.08
    ি
    -0.08
     Da
    -0.08
     Haar
    -0.08
    ormon
    -0.08
     hospice
    -0.07
     sauna
    -0.07
    선
    -0.07
    ுகிற
    -0.07
    POSITIVE LOGITS
    fully
    0.10
     deceit
    0.09
     camouflage
    0.09
    妙
    0.09
     craftsmanship
    0.08
    巧
    0.08
    fulness
    0.08
     stealth
    0.08
    efficient
    0.08
     pédagogique
    0.08
    Activations Density 0.009%

    No Known Activations