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. 77198
    Prev
    Next
    INDEX
    Explanations

    using emotions

    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
     ოც
    -0.08
    .restart
    -0.08
     teardown
    -0.08
    ்க்க
    -0.08
    (nameof
    -0.08
    (Add
    -0.08
    (static
    -0.08
    ачи
    -0.08
    (original
    -0.07
    (row
    -0.07
    POSITIVE LOGITS
     olmak
    0.07
     calon
    0.07
    Crypt
    0.07
    Ym
    0.07
     Gmb
    0.07
    еу
    0.07
     grids
    0.07
     Gru
    0.07
    bə
    0.07
     cyn
    0.07
    Activations Density 0.000%

    No Known Activations