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. 102994
    Prev
    Next
    INDEX
    Explanations

    net worth

    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
    appear
    -0.07
     punctuation
    -0.07
     препят
    -0.07
     eile
    -0.07
     tense
    -0.07
     reels
    -0.07
     polymer
    -0.07
    horn
    -0.07
     Polymer
    -0.07
     publisher
    -0.07
    POSITIVE LOGITS
     concierge
    0.11
     affluent
    0.10
     wealthy
    0.10
     billionaire
    0.09
     Concierge
    0.09
     ಶ್ರೀ
    0.09
     catered
    0.09
     عبدال
    0.09
     سعود
    0.09
     philanth
    0.09
    Activations Density 0.008%

    No Known Activations