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. 43295
    Prev
    Next
    INDEX
    Explanations

    Important

    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
     parted
    -0.09
     overcame
    -0.08
     forfe
    -0.08
     barrier
    -0.07
     hormona
    -0.07
     curse
    -0.07
     deelt
    -0.07
     wab
    -0.07
     Barr
    -0.07
     craw
    -0.07
    POSITIVE LOGITS
    VIP
    0.10
    Treatment
    0.09
     सम्मान
    0.08
     VIP
    0.08
     tratamento
    0.08
     apprécié
    0.08
     ಗೌ
    0.08
     trattamento
    0.08
     уник
    0.08
     പ്ര
    0.08
    Activations Density 0.054%

    No Known Activations