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. 49221
    Prev
    Next
    INDEX
    Explanations

    filter

    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
    `↵↵
    -0.08
    `:
    -0.08
     clogged
    -0.08
     standings
    -0.07
    -follow
    -0.07
     validations
    -0.07
     erros
    -0.07
     Access
    -0.07
     المعارضة
    -0.07
     acces
    -0.07
    POSITIVE LOGITS
     polyurethane
    0.08
    ecc
    0.08
     št
    0.08
    Pent
    0.08
     berb
    0.08
     trí
    0.08
    国
    0.08
    Sie
    0.07
     suisse
    0.07
     berlangsung
    0.07
    Activations Density 0.001%

    No Known Activations