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. 44121
    Prev
    Next
    INDEX
    Explanations

    Percentage reductions

    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
     poems
    -0.09
     dalje
    -0.08
     마음
    -0.08
     buzzing
    -0.08
     benutzt
    -0.07
     dipl
    -0.07
     coy
    -0.07
     digunakan
    -0.07
     ع
    -0.07
    artits
    -0.07
    POSITIVE LOGITS
     percentual
    0.12
     Reduction
    0.12
     réduction
    0.11
     reductions
    0.11
     reduction
    0.11
    Reduction
    0.11
     Percentage
    0.11
    %.↵
    0.10
    .percent
    0.10
     redução
    0.10
    Activations Density 0.016%

    No Known Activations