© 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. 79231
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    ��
    -0.09
     Bert
    -0.08
     ideaal
    -0.08
     ಗೌ
    -0.08
    _CN
    -0.08
    ิร์
    -0.08
    inse
    -0.08
     advancement
    -0.08
    �
    -0.07
     propon
    -0.07
    POSITIVE LOGITS
     negatives
    0.11
     negativos
    0.10
     Negative
    0.09
    -negative
    0.09
     negative
    0.09
     risk
    0.09
     valent
    0.09
    风险
    0.09
    negative
    0.09
     negativo
    0.08
    Activations Density 0.018%

    No Known Activations