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. 43129
    Prev
    Next
    INDEX
    Explanations

    breaking or damage

    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
     crest
    -0.08
     génére
    -0.08
     gull
    -0.08
    Expect
    -0.08
    ಿಸಲಾಗಿದೆ
    -0.08
     يبدو
    -0.07
     JDBC
    -0.07
    zx
    -0.07
     klok
    -0.07
    Susp
    -0.07
    POSITIVE LOGITS
     بسبب
    0.11
     pitfalls
    0.10
    怎么办
    0.10
     akibat
    0.10
     aufgrund
    0.10
    たり
    0.09
     undue
    0.09
    -proof
    0.09
    due
    0.09
     due
    0.09
    Activations Density 0.271%

    No Known Activations