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. 111386
    Prev
    Next
    INDEX
    Explanations

    i

    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
     Centrum
    -0.10
     Sanders
    -0.08
     씨
    -0.08
    ,以
    -0.08
     Saber
    -0.07
     Deutsch
    -0.07
    ecera
    -0.07
     Apples
    -0.07
     Farmer
    -0.07
    ako
    -0.07
    POSITIVE LOGITS
    ные
    0.08
    -প
    0.08
    (_)
    0.08
    -п
    0.07
     lur
    0.07
    -positive
    0.07
    Vent
    0.07
    -vol
    0.07
    ('').
    0.07
    423
    0.07
    Activations Density 0.007%

    No Known Activations