Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9081
    Prev
    Next
    INDEX
    Explanations

    Naming things

    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
     veille
    -0.07
     disent
    -0.07
     on
    -0.07
    ума
    -0.07
    审核
    -0.07
     البحث
    -0.07
    epy
    -0.07
    elis
    -0.07
    éma
    -0.07
     však
    -0.07
    POSITIVE LOGITS
     pangalan
    0.09
     nombr
    0.09
    ingss
    0.09
     nomen
    0.09
    名稱
    0.09
    	names
    0.09
     bezeichnet
    0.09
    名称
    0.09
     teny
    0.08
     navn
    0.08
    Activations Density 0.006%

    No Known Activations