Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 52697
    Prev
    Next
    INDEX
    Explanations

    dynamic SQL 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
    ിട്ട
    -0.08
    ափ
    -0.08
    upp
    -0.08
    湿
    -0.08
    Conflict
    -0.07
    вяз
    -0.07
     obligatory
    -0.07
    ுள
    -0.07
    용
    -0.07
    肃
    -0.07
    POSITIVE LOGITS
    字符串
    0.10
     dynamically
    0.10
    -string
    0.10
     dinám
    0.10
     문자열
    0.10
    /string
    0.09
     गत
    0.09
     concaten
    0.08
     dinámica
    0.08
     literally
    0.08
    Activations Density 0.009%

    No Known Activations