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. 12916
    Prev
    Next
    INDEX
    Explanations

    removable

    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
     bold
    -0.08
    -bold
    -0.07
     objectives
    -0.07
    忙
    -0.07
     zeal
    -0.07
    ident
    -0.07
    ml
    -0.07
    angar
    -0.07
    Wow
    -0.07
    ength
    -0.07
    POSITIVE LOGITS
     miti
    0.09
     Bennett
    0.09
     removable
    0.08
     задан
    0.08
     teeb
    0.08
     fenô
    0.08
     dahilan
    0.08
     అనంత
    0.08
     Dha
    0.08
    핑
    0.08
    Activations Density 0.001%

    No Known Activations