Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 56166
    Prev
    Next
    INDEX
    Explanations

    Horizontal dividers

    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
     Hubbard
    -0.09
     Dutch
    -0.09
     MOS
    -0.08
    _BTN
    -0.08
    仪
    -0.08
     Cele
    -0.07
     Hagen
    -0.07
    Dutch
    -0.07
     souvenirs
    -0.07
    CAT
    -0.07
    POSITIVE LOGITS
    가
    0.09
     ειδ
    0.08
     Reform
    0.08
     denunci
    0.07
     참고
    0.07
     보고
    0.07
    оволь
    0.07
    ங்கை
    0.07
     cringe
    0.07
     போ
    0.07
    Activations Density 0.014%

    No Known Activations