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. 76462
    Prev
    Next
    INDEX
    Explanations

    rich

    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
     maxim
    -0.08
    <IC
    -0.08
     Strict
    -0.08
    Fresh
    -0.07
     Sold
    -0.07
    ailym
    -0.07
    €‰
    -0.07
     überzeugt
    -0.07
     비롯
    -0.07
    үр
    -0.07
    POSITIVE LOGITS
     facilitating
    0.08
    裕
    0.08
     wealth
    0.08
     clientele
    0.08
     શકો
    0.07
     वर्ग
    0.07
     enabling
    0.07
     facilitate
    0.07
    阶
    0.07
    lərin
    0.07
    Activations Density 0.028%

    No Known Activations