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. 53919
    Prev
    Next
    INDEX
    Explanations

    buttons and UI

    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
     infestation
    -0.09
     mant
    -0.09
     준
    -0.08
     intel
    -0.08
    쓴
    -0.08
     dumped
    -0.08
     lim
    -0.08
    INT
    -0.08
     exploited
    -0.08
     firsthand
    -0.07
    POSITIVE LOGITS
    按钮
    0.22
     кноп
    0.20
     button
    0.19
     botón
    0.19
     버튼
    0.19
     кнопку
    0.19
    .button
    0.18
    	button
    0.18
    button
    0.18
    _button
    0.17
    Activations Density 0.032%

    No Known Activations