© 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. 11-RESID-POST-AA
    6. 25005
    Prev
    Next
    INDEX
    Explanations

    signals

    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
    _med
    -0.08
     在线
    -0.08
     Corre
    -0.08
    .Full
    -0.08
    אב
    -0.07
    .Access
    -0.07
     ağ
    -0.07
    afb
    -0.07
     Correction
    -0.07
     মাল
    -0.07
    POSITIVE LOGITS
     readiness
    0.11
     preparar
    0.10
     подготов
    0.10
     подготовки
    0.10
     તૈયાર
    0.10
     તૈય
    0.10
     준비
    0.10
     preparedness
    0.10
    เข้าส
    0.10
     संक्रमण
    0.10
    Activations Density 0.007%

    No Known Activations