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. 30655
    Prev
    Next
    INDEX
    Explanations

    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
     ques
    -0.08
    /q
    -0.07
     ക്ഷ
    -0.07
    pect
    -0.07
    _PL
    -0.07
    Hunter
    -0.07
    、安全
    -0.07
     മാന
    -0.07
    .q
    -0.07
     jü
    -0.07
    POSITIVE LOGITS
    alaa
    0.08
    交易
    0.08
    тый
    0.07
    odynamic
    0.07
     карти
    0.07
     stool
    0.07
     컬
    0.07
    инар
    0.07
    col
    0.07
    лис
    0.07
    Activations Density 0.016%

    No Known Activations