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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 44902
    Prev
    Next
    INDEX
    Explanations

    Code, programming

    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
    **/↵↵
    -0.09
    �
    -0.08
     aerodynamic
    -0.08
    ензи
    -0.08
     REQUIRE
    -0.08
    .chdir
    -0.07
    ５０
    -0.07
    ಠ
    -0.07
     court
    -0.07
     CH
    -0.07
    POSITIVE LOGITS
    》、《
    0.09
     آر
    0.08
    asy
    0.08
    」、「
    0.08
    peating
    0.08
     plumbing
    0.08
    ocas
    0.07
    housing
    0.07
     пригод
    0.07
    และ
    0.07
    Activations Density 0.008%

    No Known Activations