© 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. 99741
    Prev
    Next
    INDEX
    Explanations

    Non-English text

    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
    opher
    -0.09
    ocoder
    -0.08
    ortex
    -0.08
    pand
    -0.08
    .Infof
    -0.08
    busters
    -0.08
     estaciones
    -0.08
     vessels
    -0.07
     Sm
    -0.07
    عبة
    -0.07
    POSITIVE LOGITS
     approfond
    0.12
     studies
    0.10
     conducted
    0.09
     estudo
    0.09
    Studies
    0.09
     aprofund
    0.09
     अध्ययन
    0.09
    研究
    0.09
     estudos
    0.09
     estudio
    0.09
    Activations Density 0.021%

    No Known Activations