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. 15-RESID-POST-AA
    6. 19415
    Prev
    Next
    INDEX
    Explanations

    guarantee

    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
    rray
    -0.08
    (Vector
    -0.08
     Ignacio
    -0.08
     accumulating
    -0.08
     accumulate
    -0.07
     nhóm
    -0.07
     Habana
    -0.07
    cljs
    -0.07
     잠
    -0.07
     desayuno
    -0.07
    POSITIVE LOGITS
    保証
    0.20
     guarantee
    0.20
     guarantees
    0.19
    Guarante
    0.19
     Guarantee
    0.19
     Guarante
    0.18
     гаран
    0.18
     garantie
    0.18
    Guaranteed
    0.17
     garantit
    0.17
    Activations Density 0.044%

    No Known Activations