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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 64622
    Prev
    Next
    INDEX
    Explanations

    ible

    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
     Pipes
    -0.08
     kome
    -0.08
     Pipeline
    -0.08
    enegro
    -0.07
     لجنة
    -0.07
    .python
    -0.07
     Commission
    -0.07
     आयोग
    -0.07
     Peek
    -0.07
     fung
    -0.07
    POSITIVE LOGITS
     fragmented
    0.12
     truncated
    0.11
     corrupted
    0.10
     incomplete
    0.10
    乱码
    0.10
    途中
    0.10
     fragments
    0.10
     interrupted
    0.10
    uncated
    0.09
    遮
    0.09
    Activations Density 0.091%

    No Known Activations