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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 106004
    Prev
    Next
    INDEX
    Explanations

    2

    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
    ิก
    -0.08
    另类
    -0.08
    此同时
    -0.08
    .za
    -0.08
    antry
    -0.08
     gärna
    -0.08
    аныш
    -0.07
    lıklı
    -0.07
    .transparent
    -0.07
     Clerk
    -0.07
    POSITIVE LOGITS
    )))
    0.08
     خواب
    0.08
    ceil
    0.08
     ahụ
    0.08
    )=
    0.07
    関連
    0.07
    976
    0.07
    ]>=
    0.07
     éta
    0.07
     Berger
    0.07
    Activations Density 0.024%

    No Known Activations