© 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. 44584
    Prev
    Next
    INDEX
    Explanations

    es

    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
    -nine
    -0.08
     atrocities
    -0.08
     nunca
    -0.07
    的人
    -0.07
     Cere
    -0.07
    Never
    -0.07
     terrified
    -0.07
     sticking
    -0.07
     torture
    -0.07
     Tensor
    -0.07
    POSITIVE LOGITS
     parlar
    0.08
     apples
    0.08
    unas
    0.08
    113
    0.07
    рост
    0.07
     pans
    0.07
     Beck
    0.07
     kaynak
    0.07
     classic
    0.07
    _LT
    0.07
    Activations Density 0.006%

    No Known Activations