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. 120283
    Prev
    Next
    INDEX
    Explanations

    Air

    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
    とも
    -0.09
    ,此
    -0.08
     ebenfalls
    -0.08
    睛
    -0.08
     الاول
    -0.08
     fes
    -0.08
     trat
    -0.08
     massively
    -0.07
    /SP
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    dig
    0.08
    �
    0.07
    burn
    0.07
    성과
    0.07
    -shaped
    0.07
     Money
    0.07
    eland
    0.07
    max
    0.07
    ந
    0.07
     în
    0.07
    Activations Density 1.181%

    No Known Activations