© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 108257
    Prev
    Next
    INDEX
    Explanations

    computer specifications

    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
     tiltak
    -0.08
     cosmetics
    -0.08
     !!!!
    -0.08
     EMAIL
    -0.08
     Tattoos
    -0.08
     cinta
    -0.08
     حادث
    -0.08
     pelu
    -0.08
    алӣ
    -0.08
    .EMAIL
    -0.08
    POSITIVE LOGITS
     CPUs
    0.13
     Ryzen
    0.11
     Intel
    0.11
     chipset
    0.10
    Intel
    0.10
     processors
    0.10
     engines
    0.10
    processors
    0.09
     Engines
    0.09
     GHz
    0.09
    Activations Density 0.027%

    No Known Activations