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. 19524
    Prev
    Next
    INDEX
    Explanations

    opens

    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
    -US
    -0.08
    AK
    -0.07
    MS
    -0.07
    Friend
    -0.07
    ensi
    -0.07
    そ
    -0.07
    altime
    -0.07
    EMS
    -0.07
     Has
    -0.07
    MN
    -0.07
    POSITIVE LOGITS
     convince
    0.10
     ø
    0.08
     convencer
    0.08
    又黄
    0.08
    ുറം
    0.08
    ावरण
    0.08
     convincing
    0.08
                ↵↵
    0.08
     फिल्म
    0.08
     beveilig
    0.08
    Activations Density 0.000%

    No Known Activations