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

    Neuronpedia

    APICircuit 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. 60807
    Prev
    Next
    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash

    passages about dreams and their interpretation, especially vivid or symbolic pregnancy/birth-themed dream narratives.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    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
     steaks
    -0.08
     الأع
    -0.08
    'A
    -0.08
     masu
    -0.08
    AYS
    -0.08
     sicuramente
    -0.08
    _LINE
    -0.08
    "A
    -0.07
    '][$
    -0.07
    \Order
    -0.07
    POSITIVE LOGITS
     emotionally
    0.10
     imagining
    0.09
     꿈
    0.08
    nh
    0.08
     vividly
    0.08
     somehow
    0.08
     spontaneously
    0.08
     mentally
    0.07
    igent
    0.07
     garments
    0.07
    Activations Density 0.046%

    No Known Activations