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. 55977
    Prev
    Next
    INDEX
    Explanations

    Johnson

    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
     Divide
    -0.08
     Grote
    -0.08
     গ্র
    -0.08
     الد
    -0.08
     Palermo
    -0.08
     الذي
    -0.07
     Harmon
    -0.07
     盛
    -0.07
    ಿಮ
    -0.07
    ಂತರ
    -0.07
    POSITIVE LOGITS
     Rifle
    0.09
    ibles
    0.08
    292
    0.08
     sentences
    0.07
    :req
    0.07
    bib
    0.07
    isis
    0.07
     specif
    0.07
     specifications
    0.07
    001
    0.07
    Activations Density 0.000%

    No Known Activations