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. 120389
    Prev
    Next
    INDEX
    Explanations

    Mistakes happen

    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
     başlam
    -0.09
     auprès
    -0.08
    preh
    -0.08
     Gh
    -0.07
    Allowed
    -0.07
    prim
    -0.07
    ANDA
    -0.07
     gehol
    -0.07
     handlebars
    -0.07
     entendre
    -0.07
    POSITIVE LOGITS
     inevitably
    0.19
     imperfections
    0.14
     invariably
    0.13
     inevitable
    0.13
     imperfect
    0.11
     inevit
    0.10
     undoubtedly
    0.10
     бывает
    0.10
     forcément
    0.10
     irgendwann
    0.10
    Activations Density 0.143%

    No Known Activations