© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89
    Prev
    Next
    INDEX
    Explanations

    3D modeling indices/triangles

    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
     Domingo
    -0.08
     pade
    -0.07
     հաս
    -0.07
     getenv
    -0.07
     memperoleh
    -0.07
     solar
    -0.07
     undercover
    -0.07
     продуктов
    -0.07
     Napoleon
    -0.07
    Sess
    -0.07
    POSITIVE LOGITS
    Indices
    0.15
    _indices
    0.14
    (indices
    0.13
    indices
    0.13
    .indices
    0.13
    Ids
    0.12
     indices
    0.11
    (ids
    0.10
     IDs
    0.10
    _ids
    0.10
    Activations Density 0.012%

    No Known Activations