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. 65118
    Prev
    Next
    INDEX
    Explanations

    coding errors

    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
    _PAD
    -0.08
    itas
    -0.08
     bedside
    -0.07
     undergoing
    -0.07
     yourself
    -0.07
     کنید
    -0.07
     Led
    -0.07
     fondos
    -0.07
    őség
    -0.07
    -focused
    -0.07
    POSITIVE LOGITS
     automáticamente
    0.10
     തന്റെ
    0.10
     தனது
    0.10
     automatiquement
    0.10
     करेगा
    0.09
     ತನ್ನ
    0.09
     yaptığı
    0.09
     dut
    0.09
    encrypt
    0.09
    检测
    0.09
    Activations Density 0.129%

    No Known Activations