© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 13421
    Prev
    Next
    INDEX
    Explanations

    CSV writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    째
    -0.09
     лек
    -0.08
     фирмы
    -0.08
     ×
    -0.07
     Wig
    -0.07
    锐
    -0.07
    ächen
    -0.07
    _BASE
    -0.07
    ½
    -0.07
    今晚
    -0.07
    POSITIVE LOGITS
     Malt
    0.08
    okan
    0.08
     inhal
    0.08
    EM
    0.07
     nurturing
    0.07
     God
    0.07
    George
    0.07
     Marion
    0.07
     videojuegos
    0.07
    atil
    0.07
    Activations Density 0.000%

    No Known Activations