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. 112959
    Prev
    Next
    INDEX
    Explanations

    ическими

    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
     saum
    -0.08
     Except
    -0.07
    -I
    -0.07
    ..↵↵
    -0.07
    Iss
    -0.07
     Cord
    -0.07
    ulle
    -0.07
     poter
    -0.07
    日は
    -0.07
     Death
    -0.07
    POSITIVE LOGITS
     maupun
    0.18
     לבין
    0.12
     וגם
    0.12
    还是
    0.11
     ataupun
    0.11
     είτε
    0.11
     oppure
    0.10
     وبين
    0.10
     vừa
    0.09
     nor
    0.09
    Activations Density 0.334%

    No Known Activations