© 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. 47877
    Prev
    Next
    INDEX
    Explanations

    atos

    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
     résumé
    -0.08
     cứ
    -0.07
     interfaz
    -0.07
    (interval
    -0.07
    接口
    -0.07
    -0.07
     mentor
    -0.07
    ഡിയ
    -0.07
    เรีย
    -0.07
    地下
    -0.07
    POSITIVE LOGITS
     Cleanup
    0.08
     far
    0.08
    pur
    0.08
     ungewöhn
    0.08
     Published
    0.08
     grau
    0.08
    far
    0.08
     Garbage
    0.08
     FAR
    0.08
     வரை
    0.07
    Activations Density 0.002%
    No Known Activations