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. 15-RESID-POST-AA
    6. 149
    Prev
    Next
    INDEX
    Explanations

    Wanting

    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
    :@
    -0.07
     donated
    -0.07
    機
    -0.07
     technischen
    -0.07
     flown
    -0.07
    ,null
    -0.07
     amended
    -0.07
     verlo
    -0.06
    ,a
    -0.06
     반환
    -0.06
    POSITIVE LOGITS
     غواړي
    0.13
     хочет
    0.13
     يريد
    0.12
     хотят
    0.12
     quieren
    0.12
     wants
    0.11
     चाहते
    0.11
     nhằm
    0.11
     versuchen
    0.11
     कोशिश
    0.10
    Activations Density 0.304%

    No Known Activations