© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 24759
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
     আমি
    -0.10
     నేను
    -0.08
    ujesz
    -0.08
     હું
    -0.08
     considero
    -0.08
     tienes
    -0.08
     ನಾನು
    -0.08
    শেষ
    -0.08
     είτε
    -0.08
     arrest
    -0.08
    POSITIVE LOGITS
     sometimes
    0.13
     ibland
    0.12
     parfois
    0.11
    Sometimes
    0.11
    习
    0.11
    sometimes
    0.10
     manchmal
    0.10
     occasionally
    0.10
     notation
    0.10
     soms
    0.10
    Activations Density 0.031%

    No Known Activations