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. 56151
    Prev
    Next
    INDEX
    Explanations

    出现

    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
    irl
    -0.08
    断
    -0.08
    (IR
    -0.08
     imun
    -0.07
     que
    -0.07
     conjug
    -0.07
     relação
    -0.07
     ద
    -0.07
     llevaron
    -0.07
     forhold
    -0.07
    POSITIVE LOGITS
     запрещ
    0.10
    は禁止
    0.09
     prohibition
    0.09
     slavery
    0.09
     forbidden
    0.09
    禁止
    0.09
    Forbidden
    0.09
     taboo
    0.08
     verboden
    0.08
    ാത
    0.08
    Activations Density 0.001%

    No Known Activations