Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 7-RESID-POST-AA
    6. 131057
    Prev
    Next
    INDEX
    Explanations

    goes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    одав
    -0.08
    mel
    -0.08
    Svc
    -0.08
    svc
    -0.07
    bole
    -0.07
    som
    -0.07
     sobre
    -0.07
    Mel
    -0.07
    ล
    -0.07
     lad
    -0.07
    POSITIVE LOGITS
     Stair
    0.08
     മാറ
    0.08
     []
    0.08
    acu
    0.08
    一级
    0.08
     barren
    0.07
     increases
    0.07
     References
    0.07
     Autodesk
    0.07
     Rising
    0.07
    Activations Density 0.005%

    No Known Activations