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. 15-RESID-POST-AA
    6. 18978
    Prev
    Next
    INDEX
    Explanations

    Or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     లేదా
    -0.12
     або
    -0.11
     или
    -0.11
    /or
    -0.11
     hoặc
    -0.11
     किंवा
    -0.11
     oder
    -0.10
     alebo
    -0.10
     atau
    -0.10
    /oder
    -0.10
    POSITIVE LOGITS
     importantly
    0.13
     could
    0.10
     вообще
    0.10
     purposely
    0.10
     would
    0.09
     it's
    0.09
     simply
    0.09
    就是说
    0.09
     اینکه
    0.09
     juist
    0.08
    Activations Density 0.033%

    No Known Activations