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. 78660
    Prev
    Next
    INDEX
    Explanations

    Repeating decimals in calculations

    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
    348
    -0.08
     confirmation
    -0.08
     prec
    -0.07
    �
    -0.07
    MK
    -0.07
     scanners
    -0.07
     heat
    -0.07
     checksum
    -0.07
    Iso
    -0.07
     لذلك
    -0.07
    POSITIVE LOGITS
    වැ
    0.09
    ào
    0.09
    ================================================================================
    0.09
    Factory
    0.08
    fortawesome
    0.08
    දී
    0.08
    து
    0.08
    මෙ
    0.08
     Ow
    0.08
    .githubusercontent
    0.08
    Activations Density 0.026%

    No Known Activations