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. 7-RESID-POST-AA
    6. 131026
    Prev
    Next
    INDEX
    Explanations

    April

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    @param
    -0.09
     eka
    -0.08
    骗局吗
    -0.08
     mæ
    -0.08
     müm
    -0.08
    ]string
    -0.08
     rink
    -0.08
     mutane
    -0.08
    ============↵
    -0.07
    وڑ
    -0.07
    POSITIVE LOGITS
     ఆ
    0.08
    ultur
    0.08
    431
    0.07
    169
    0.07
    г
    0.07
    435
    0.07
    fr
    0.07
    Amount
    0.07
     Anton
    0.07
    assoc
    0.07
    Activations Density 0.004%

    No Known Activations