© 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. 108588
    Prev
    Next
    INDEX
    Explanations

    ness

    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
    Nam
    -0.09
    čno
    -0.08
    wm
    -0.08
    ’m
    -0.08
    Men
    -0.08
     pagos
    -0.07
    pag
    -0.07
    hr
    -0.07
     pig
    -0.07
     parab
    -0.07
    POSITIVE LOGITS
     FY
    0.08
    рыл
    0.08
     сов
    0.08
    กระ
    0.07
     الأس
    0.07
     Pres
    0.07
     permitted
    0.07
    �
    0.07
     Perth
    0.07
     Kay
    0.07
    Activations Density 0.037%

    No Known Activations