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. 12015
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Sp
    -0.08
    गर
    -0.08
    ना
    -0.08
    却
    -0.08
     হলেও
    -0.07
    amu
    -0.07
     गए
    -0.07
    municip
    -0.07
    _Params
    -0.07
     Rim
    -0.07
    POSITIVE LOGITS
     aşk
    0.08
     Ereign
    0.08
     Mannschaft
    0.08
    IPH
    0.08
     literally
    0.07
     eure
    0.07
    ικο
    0.07
     recours
    0.07
    ောက်
    0.07
    ορ
    0.07
    Activations Density 0.038%

    No Known Activations