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. 9161
    Prev
    Next
    INDEX
    Explanations

    -

    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
    етті
    -0.08
     programu
    -0.08
    program
    -0.08
    黄
    -0.08
    emies
    -0.08
     chương
    -0.07
    china
    -0.07
    005
    -0.07
    渡
    -0.07
    576
    -0.07
    POSITIVE LOGITS
     logarith
    0.11
     ஓ
    0.08
    )s
    0.07
     লগ
    0.07
    Ios
    0.07
    "s
    0.07
     переговор
    0.07
    0.07
    .log
    0.07
    (copy
    0.07
    Activations Density 0.005%

    No Known Activations