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

    Neuronpedia

    APICircuit 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. 75926
    Prev
    Next
    INDEX
    Explanations

    Hyphens in parentheses

    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
     र
    -0.08
     MPL
    -0.07
     ये
    -0.07
     ста
    -0.07
    .Temp
    -0.07
     द
    -0.07
    #line
    -0.07
    Iterator
    -0.07
     আর
    -0.07
     turnaround
    -0.07
    POSITIVE LOGITS
    吕
    0.09
     pina
    0.08
    ains
    0.08
    یا
    0.08
    ancis
    0.08
    366
    0.08
     приобр
    0.08
     louis
    0.08
    ден
    0.08
     瑞
    0.07
    Activations Density 0.316%

    No Known Activations