© 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. 29488
    Prev
    Next
    INDEX
    Explanations

    multiples calculation

    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
     KP
    -0.09
    _dic
    -0.07
    ारण
    -0.07
     HK
    -0.07
    .pnl
    -0.07
     kyr
    -0.07
     ku
    -0.07
    �
    -0.07
    Sil
    -0.07
     KNR
    -0.07
    POSITIVE LOGITS
    Ï
    0.08
    مون
    0.08
    Vanaf
    0.08
     impul
    0.07
     throwable
    0.07
     vanaf
    0.07
    武
    0.07
    Benchmark
    0.07
     readable
    0.07
     memo
    0.07
    Activations Density 0.015%

    No Known Activations