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. 106318
    Prev
    Next
    INDEX
    Explanations

    So

    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
     pensamientos
    -0.08
    811
    -0.08
     Harr
    -0.08
    588
    -0.08
    816
    -0.08
     将
    -0.07
     interessantes
    -0.07
    859
    -0.07
     Heb
    -0.07
    809
    -0.07
    POSITIVE LOGITS
     precedent
    0.10
     같이
    0.09
    igrant
    0.08
    なので
    0.07
    iril
    0.07
     previous
    0.07
     gewohnt
    0.07
    typedef
    0.07
    acceptable
    0.07
     shady
    0.07
    Activations Density 0.008%

    No Known Activations