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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 64099
    Prev
    Next
    INDEX
    Explanations

    policy

    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
    Cube
    -0.08
     Ambient
    -0.08
    _cube
    -0.08
     ambient
    -0.08
    共有
    -0.08
    性质
    -0.08
    Floor
    -0.08
    .entry
    -0.08
     данный
    -0.07
     tras
    -0.07
    POSITIVE LOGITS
     gewährleisten
    0.10
    -benar
    0.10
     capaz
    0.09
    tim
    0.08
    及时
    0.08
     capable
    0.08
     preferably
    0.08
     있도록
    0.08
     timely
    0.08
     باد
    0.08
    Activations Density 0.296%

    No Known Activations