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. 58983
    Prev
    Next
    INDEX
    Explanations

    slope

    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
    .att
    -0.07
     ағ
    -0.07
     ben
    -0.07
     bah
    -0.07
     troubles
    -0.07
     Ito
    -0.07
    ben
    -0.07
     expatri
    -0.07
     envelop
    -0.07
    .eng
    -0.07
    POSITIVE LOGITS
     pendiente
    0.09
     ridge
    0.08
     curvature
    0.08
    trajectory
    0.07
     adelante
    0.07
    Towards
    0.07
     nes
    0.07
     extrema
    0.07
    urized
    0.07
    滑
    0.07
    Activations Density 0.013%

    No Known Activations