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. 46918
    Prev
    Next
    INDEX
    Explanations

    viii

    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
    ackbar
    -0.07
    认为
    -0.07
     fauteuil
    -0.07
    挂机
    -0.07
    Wd
    -0.07
     CBT
    -0.07
    ば
    -0.07
    აპ
    -0.07
    闲
    -0.07
     wicker
    -0.07
    POSITIVE LOGITS
     divor
    0.08
     SAMPLE
    0.08
     prób
    0.08
     आकर्ष
    0.08
     alimentaires
    0.08
    .mime
    0.08
     murdering
    0.08
     परिवर्तन
    0.08
     juggling
    0.08
     trailer
    0.07
    Activations Density 0.003%

    No Known Activations