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. 53326
    Prev
    Next
    INDEX
    Explanations

    job announcements

    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
     inequalities
    -0.08
     correl
    -0.08
    Destroy
    -0.07
    ORN
    -0.07
    Observation
    -0.07
     уничтож
    -0.07
    Observ
    -0.07
    оди
    -0.07
    ológ
    -0.07
     तुलना
    -0.07
    POSITIVE LOGITS
    新增
    0.11
     ایش
    0.10
     chaleure
    0.10
     bienvenida
    0.09
     toegevoegd
    0.09
    添加
    0.09
     welcoming
    0.09
    加入
    0.09
     الجديد
    0.09
    _added
    0.09
    Activations Density 0.113%

    No Known Activations