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. 113787
    Prev
    Next
    INDEX
    Explanations

    Improvement

    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
     SNP
    -0.08
    oul
    -0.08
     signatures
    -0.08
     respective
    -0.07
    peech
    -0.07
    가지
    -0.07
     Mn
    -0.07
     tru
    -0.07
     면
    -0.07
    分页
    -0.07
    POSITIVE LOGITS
     Beirut
    0.09
     undertaken
    0.08
     Zagreb
    0.08
     recomendar
    0.08
     recomiendo
    0.08
     Balcony
    0.08
     daquele
    0.08
    >Status
    0.07
    .”↵↵
    0.07
     המכ
    0.07
    Activations Density 0.521%

    No Known Activations