© 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. 48734
    Prev
    Next
    INDEX
    Explanations

    �

    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
    后
    -0.09
    後
    -0.08
    λλά
    -0.07
     tal
    -0.07
     Trent
    -0.07
    ياً
    -0.07
    अ
    -0.07
     Tyson
    -0.07
     مض
    -0.07
     vnode
    -0.07
    POSITIVE LOGITS
    NORMAL
    0.10
    �
    0.08
    _normal
    0.08
     NORMAL
    0.08
    drops
    0.08
    tasks
    0.08
    SOC
    0.08
    ています
    0.08
    ��
    0.08
    Soph
    0.08
    Activations Density 0.000%

    No Known Activations