© 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. 99727
    Prev
    Next
    INDEX
    Explanations

    fear

    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
     tangu
    -0.09
    ẵn
    -0.09
    ông
    -0.08
    érez
    -0.08
     hent
    -0.08
    іні
    -0.08
     tensão
    -0.08
     tensions
    -0.08
    .gen
    -0.08
    аном
    -0.08
    POSITIVE LOGITS
    失
    0.10
     खो
    0.10
     losing
    0.10
     risking
    0.09
     നഷ്ട
    0.09
     Losing
    0.09
     backlash
    0.09
     lose
    0.09
     слишком
    0.08
     nanti
    0.08
    Activations Density 0.075%

    No Known Activations