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. 15-RESID-POST-AA
    6. 19521
    Prev
    Next
    INDEX
    Explanations

    our

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emetery
    -0.09
     turnovers
    -0.09
     개인
    -0.08
     rentrer
    -0.08
    دارية
    -0.08
     ব্যক্ত
    -0.08
     יד
    -0.08
     ব্যক্তি
    -0.08
    دوية
    -0.08
     заряд
    -0.08
    POSITIVE LOGITS
     G
    0.08
     AT
    0.08
    an
    0.08
     i
    0.08
     he
    0.08
     from
    0.08
    akin
    0.08
     
    0.08
     N
    0.08
     Atl
    0.08
    Activations Density 0.165%

    No Known Activations