© 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. 23-RESID-POST-AA
    11. 97525
    Prev
    Next
    INDEX
    Explanations

    O

    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
     зависимости
    -0.09
     dolayı
    -0.09
    ადგ
    -0.09
     والخ
    -0.09
    алт
    -0.08
    <|constrain|>
    -0.08
     حول
    -0.08
     وبالتالي
    -0.08
    ებ
    -0.08
    ەپ
    -0.08
    POSITIVE LOGITS
    verture
    0.12
    ’clock
    0.11
    'clock
    0.11
     Superman
    0.11
    ath
    0.11
    skar
    0.11
    asis
    0.11
    hlala
    0.10
    wl
    0.10
    men
    0.10
    Activations Density 0.011%

    No Known Activations