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. 45272
    Prev
    Next
    INDEX
    Explanations

    then

    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
     interpersonal
    -0.09
    探索
    -0.08
    .deploy
    -0.08
     Rome
    -0.08
     juris
    -0.08
     rebellious
    -0.08
    戒
    -0.08
     tarot
    -0.08
     Bezos
    -0.08
     SWOT
    -0.08
    POSITIVE LOGITS
     endian
    0.13
     shaders
    0.11
    Endian
    0.11
     SIMD
    0.11
    _stride
    0.11
    _RGBA
    0.11
    Chunk
    0.10
    texture
    0.10
    _texture
    0.10
    Texture
    0.10
    Activations Density 0.006%

    No Known Activations