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. 42288
    Prev
    Next
    INDEX
    Explanations

    Segmentation fault/code errors

    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
     Obi
    -0.09
     Williamsburg
    -0.09
    优惠
    -0.09
     etdir
    -0.08
    優惠
    -0.08
    ્ય
    -0.08
     ભાવ
    -0.08
    Jennifer
    -0.08
     cảm
    -0.08
     sentiment
    -0.08
    POSITIVE LOGITS
    Violation
    0.12
     crashes
    0.11
     violation
    0.11
     uintptr
    0.11
    .memory
    0.11
    违规
    0.11
    (memory
    0.11
    (ptr
    0.11
    Malloc
    0.10
    ptr
    0.10
    Activations Density 0.006%

    No Known Activations