© 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. 129
    Prev
    Next
    INDEX
    Explanations

    HTTP security headers

    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
    报名
    -0.09
     reservoir
    -0.09
     salvation
    -0.09
    _INPUT
    -0.08
     inlet
    -0.08
    opedia
    -0.08
    Junior
    -0.08
     pastime
    -0.08
    רכז
    -0.08
     machining
    -0.08
    POSITIVE LOGITS
     नीति
    0.10
     encabez
    0.09
     MIME
    0.09
     политики
    0.09
    .headers
    0.09
     headers
    0.09
    Headers
    0.08
     policies
    0.08
     정책
    0.08
     سياسة
    0.08
    Activations Density 0.008%

    No Known Activations