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. 30604
    Prev
    Next
    INDEX
    Explanations

    winning

    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
    mc
    -0.08
     mc
    -0.08
     mod
    -0.07
    .windows
    -0.07
    inventory
    -0.07
     mo
    -0.07
    windows
    -0.07
     assim
    -0.07
     atten
    -0.07
    mf
    -0.07
    POSITIVE LOGITS
    -worthy
    0.11
     accolades
    0.10
     achievements
    0.10
     हासिल
    0.10
     सम्मान
    0.09
     behalen
    0.09
    Achievements
    0.09
     നേടിയ
    0.09
    -winning
    0.09
     पुरस्कार
    0.08
    Activations Density 0.087%

    No Known Activations