Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 76090
    Prev
    Next
    INDEX
    Explanations

    ine

    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
     Chr
    -0.09
     τε
    -0.08
     estructuras
    -0.08
     chr
    -0.08
     uart
    -0.08
     estruturas
    -0.08
    έ
    -0.08
    .substring
    -0.08
    ץ
    -0.07
    τος
    -0.07
    POSITIVE LOGITS
     DU
    0.08
     Boni
    0.08
    Lab
    0.08
     Fury
    0.08
    دی
    0.08
    猛
    0.07
     Ibiza
    0.07
     pocos
    0.07
     rosto
    0.07
     Diagnostics
    0.07
    Activations Density 0.000%

    No Known Activations