Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 112909
    Prev
    Next
    INDEX
    Explanations

    money

    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
    See
    -0.08
    Ignore
    -0.07
     footwear
    -0.07
     jersey
    -0.07
    -0.07
    sensor
    -0.07
     serene
    -0.07
     apt
    -0.07
    Enumer
    -0.07
    ATERIAL
    -0.07
    POSITIVE LOGITS
     winnings
    0.18
     bankroll
    0.12
     wins
    0.11
     successes
    0.11
     gains
    0.11
     જીત
    0.11
     заработать
    0.11
     victories
    0.11
     Forex
    0.11
     losses
    0.11
    Activations Density 0.012%

    No Known Activations