© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 45239
    Prev
    Next
    INDEX
    Explanations

    the

    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
     જુ
    -0.08
    .convert
    -0.07
    २०१
    -0.07
    .usermodel
    -0.07
    Crist
    -0.07
     Crist
    -0.07
    .xlsx
    -0.07
    .crm
    -0.07
     Williams
    -0.07
     Matteo
    -0.07
    POSITIVE LOGITS
     motifs
    0.08
    acters
    0.08
     tense
    0.07
    浓
    0.07
     separación
    0.07
     Mot
    0.07
    主题
    0.07
     tres
    0.07
    hashtags
    0.07
     strtoupper
    0.07
    Activations Density 0.004%

    No Known Activations