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. 103877
    Prev
    Next
    INDEX
    Explanations

    Employment calculations

    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
    ाउनु
    -0.09
    izarre
    -0.08
    -0.08
     arquitetura
    -0.08
     screenshot
    -0.08
     XOR
    -0.08
    zsche
    -0.08
     있어서
    -0.07
    此次
    -0.07
     Eso
    -0.07
    POSITIVE LOGITS
     yearly
    0.12
    Monthly
    0.11
    全年
    0.11
     annual
    0.10
    _YEAR
    0.10
     daylight
    0.10
    365
    0.10
    年間
    0.09
     jährlich
    0.09
    勤
    0.09
    Activations Density 0.028%

    No Known Activations