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. 43234
    Prev
    Next
    INDEX
    Explanations

    random

    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
     Lov
    -0.09
    ومن
    -0.08
     Plato
    -0.08
     Ty
    -0.08
     suv
    -0.07
    Shar
    -0.07
     Communist
    -0.07
     Luz
    -0.07
     Wach
    -0.07
     Poor
    -0.07
    POSITIVE LOGITS
    .randint
    0.10
    .choice
    0.09
    stuff
    0.08
    -cols
    0.08
    لىق
    0.08
    .random
    0.08
    .Next
    0.08
    Pil
    0.07
     Pil
    0.07
     fear
    0.07
    Activations Density 0.013%

    No Known Activations