© 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. 29280
    Prev
    Next
    INDEX
    Explanations

    So

    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
    orthand
    -0.09
    亦
    -0.08
    .Patient
    -0.08
     executives
    -0.08
     Executive
    -0.07
     również
    -0.07
    _WIDGET
    -0.07
    Comparison
    -0.07
     internationally
    -0.07
     എന്നും
    -0.07
    POSITIVE LOGITS
    杆
    0.08
     nec
    0.08
    §
    0.08
     melee
    0.08
     aver
    0.08
     trope
    0.08
     الحيوانات
    0.08
    বন্ধ
    0.08
     conservation
    0.08
     plantations
    0.07
    Activations Density 0.022%

    No Known Activations