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. 54040
    Prev
    Next
    INDEX
    Explanations

    image generation prompts

    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
     banken
    -0.08
    Pivot
    -0.08
     embarked
    -0.08
     Ely
    -0.07
     impover
    -0.07
    elin
    -0.07
     Banken
    -0.07
     은
    -0.07
    [obj
    -0.07
     dorp
    -0.07
    POSITIVE LOGITS
    尺寸
    0.09
     randomly
    0.09
     randint
    0.08
     Recommendation
    0.08
     uygun
    0.08
    Recommendation
    0.08
    推荐
    0.08
     empfe
    0.08
     recommand
    0.08
     recommendation
    0.08
    Activations Density 0.028%

    No Known Activations