© 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. 19-RESID-POST-AA
    11. 103025
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Huffington
    -0.09
     העוב
    -0.08
    倍投
    -0.08
     nchi
    -0.08
     Более
    -0.08
    ומי
    -0.08
     התורה
    -0.08
     СМИ
    -0.08
    文章来源
    -0.08
     纬
    -0.08
    POSITIVE LOGITS
     astronaut
    0.15
     mythical
    0.15
     futuristic
    0.15
     dragons
    0.15
     dragon
    0.14
     astronauts
    0.13
     فتاة
    0.13
    dragon
    0.13
     haunted
    0.12
     enchanted
    0.12
    Activations Density 0.024%

    No Known Activations