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. 15-RESID-POST-AA
    6. 19585
    Prev
    Next
    INDEX
    Explanations

    instructions and questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    γει
    -0.09
     Recreation
    -0.08
    િજ
    -0.08
    .protocol
    -0.08
     زد
    -0.08
     Abstand
    -0.08
    icy
    -0.08
     Father's
    -0.08
     દ
    -0.08
     اپنا
    -0.07
    POSITIVE LOGITS
    ಕ್ಕಾಗಿ
    0.08
    -return
    0.08
    /search
    0.08
    -search
    0.08
    -question
    0.07
    arski
    0.07
     fix
    0.07
     brute
    0.07
     dividend
    0.07
    ावर
    0.07
    Activations Density 0.016%

    No Known Activations