© 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. 65358
    Prev
    Next
    INDEX
    Explanations

    emoticons

    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
     appellate
    -0.09
     Regulations
    -0.09
    _Admin
    -0.09
    judul
    -0.09
    titulo
    -0.09
    प्रधान
    -0.09
     Campeonato
    -0.08
     regulations
    -0.08
     expenditures
    -0.08
     LNG
    -0.08
    POSITIVE LOGITS
    脸
    0.12
     smile
    0.12
    Smile
    0.11
     smiling
    0.11
     얼굴
    0.10
    顔
    0.10
    笑
    0.10
     facial
    0.10
     সুখ
    0.10
     :-)
    0.10
    Activations Density 0.014%

    No Known Activations