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. 90278
    Prev
    Next
    INDEX
    Explanations

    point/points

    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
    inde
    -0.08
     legit
    -0.07
     Str
    -0.07
    -এর
    -0.07
     ಜೊ
    -0.07
    Printer
    -0.07
     यांच्या
    -0.07
     luck
    -0.07
     chances
    -0.07
    uds
    -0.07
    POSITIVE LOGITS
     времени
    0.09
     Mont
    0.08
     southeast
    0.08
     этапе
    0.08
    骤
    0.08
    �
    0.08
     ঘটে
    0.08
    olone
    0.08
     adolescence
    0.08
    aneously
    0.07
    Activations Density 0.031%

    No Known Activations