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. 90228
    Prev
    Next
    INDEX
    Explanations

    信

    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
     corro
    -0.07
     DEST
    -0.07
     unfortunately
    -0.07
     softened
    -0.07
     murdered
    -0.07
     schematic
    -0.07
     vorz
    -0.07
    less
    -0.07
     specially
    -0.07
     अज
    -0.07
    POSITIVE LOGITS
     pride
    0.10
    årt
    0.09
    Able
    0.08
    pono
    0.08
    irenena
    0.08
     postura
    0.08
     ہمار
    0.08
    ances
    0.08
     confidently
    0.08
    赁
    0.08
    Activations Density 0.005%

    No Known Activations