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. 48694
    Prev
    Next
    INDEX
    Explanations

    DNA, material science

    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
    ỗ
    -0.07
    UND
    -0.07
    lon
    -0.07
     Dial
    -0.07
    token
    -0.07
    वर
    -0.07
     spokesperson
    -0.07
    -token
    -0.07
    unden
    -0.07
     स्प
    -0.07
    POSITIVE LOGITS
    Sched
    0.09
    {//
    0.09
     menet
    0.09
    >Add
    0.08
     nationalist
    0.08
     添加
    0.08
     follicles
    0.08
    _inline
    0.08
     lessen
    0.07
    Audit
    0.07
    Activations Density 0.001%

    No Known Activations