© 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. 23-RESID-POST-AA
    6. 47463
    Prev
    Next
    INDEX
    Explanations

    Yu

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nyň
    -0.09
    myzyň
    -0.09
    l
    -0.09
    sil
    -0.09
    niň
    -0.09
    збе
    -0.09
    лоо
    -0.09
    s
    -0.09
     уступ
    -0.08
    g
    -0.08
    POSITIVE LOGITS
     Heiz
    0.10
    asa
    0.10
    ornos
    0.09
    anyang
    0.09
    utako
    0.09
    eming
    0.09
    cca
    0.08
    anz
    0.08
    et
    0.08
    ెట
    0.08
    Activations Density 0.004%

    No Known Activations