Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 54970
    Prev
    Next
    INDEX
    Explanations

    higher

    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
    否
    -0.09
    Mint
    -0.08
     કેમ
    -0.08
     Côte
    -0.08
    CCC
    -0.07
    Swe
    -0.07
    оспособ
    -0.07
    Insights
    -0.07
     কয়
    -0.07
    Shop
    -0.07
    POSITIVE LOGITS
    级
    0.10
    級
    0.10
     स्तर
    0.09
    -level
    0.09
    Than
    0.08
     grade
    0.08
     cấp
    0.08
     rung
    0.08
     iterations
    0.08
     деңгей
    0.08
    Activations Density 0.013%

    No Known Activations