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. 119911
    Prev
    Next
    INDEX
    Explanations

    hypothesis testing

    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
     magazines
    -0.09
    zz
    -0.09
     sweets
    -0.09
    打造
    -0.08
     collectibles
    -0.08
    .mkdirs
    -0.08
     行
    -0.08
     few
    -0.07
     sorgt
    -0.07
     mille
    -0.07
    POSITIVE LOGITS
    Reject
    0.15
     rejecting
    0.14
     Reject
    0.13
    reject
    0.13
     reject
    0.13
     hypothesis
    0.13
     rejected
    0.12
     rejects
    0.12
     rechaz
    0.12
     rejection
    0.12
    Activations Density 0.007%

    No Known Activations