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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 106216
    Prev
    Next
    INDEX
    Explanations

    +

    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
    亿
    -0.08
     spool
    -0.08
     triste
    -0.08
     lenga
    -0.08
    ��������
    -0.08
     জীব
    -0.08
    ����
    -0.07
    彩图
    -0.07
     panneaux
    -0.07
     brick
    -0.07
    POSITIVE LOGITS
     qualific
    0.11
    _modifier
    0.10
     modifier
    0.10
     qualification
    0.10
     qualifiers
    0.09
     nominations
    0.09
     nomination
    0.09
     proficiency
    0.09
     bonuses
    0.09
     квали
    0.09
    Activations Density 0.007%

    No Known Activations