© 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. 95792
    Prev
    Next
    INDEX
    Explanations

    [

    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
    \Service
    -0.08
     दर्ज
    -0.08
     úteis
    -0.08
     koris
    -0.07
    .smtp
    -0.07
     udd
    -0.07
     applicability
    -0.07
     бей
    -0.07
     ज्ञ
    -0.07
    日消息
    -0.07
    POSITIVE LOGITS
    גד
    0.09
     കോള
    0.09
    Kol
    0.08
    נד
    0.08
     tagline
    0.08
     mittel
    0.08
     slightly
    0.07
    raj
    0.07
    პ
    0.07
     קול
    0.07
    Activations Density 0.004%

    No Known Activations