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. 78672
    Prev
    Next
    INDEX
    Explanations

    code, neighbor, time

    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
    (sb
    -0.09
    Ij
    -0.09
    Nb
    -0.09
    Longitude
    -0.08
    Anti
    -0.08
    Gender
    -0.08
    North
    -0.08
     դեմ
    -0.08
    лайды
    -0.08
    יי�
    -0.08
    POSITIVE LOGITS
     year's
    0.09
     वर्ष
    0.07
     объяс
    0.07
     मू
    0.07
     biological
    0.07
     το
    0.07
     tep
    0.07
    olocation
    0.07
     Carm
    0.07
     amount
    0.07
    Activations Density 0.000%

    No Known Activations