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. 19446
    Prev
    Next
    INDEX
    Explanations

    triangles and squares

    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
     إس
    -0.08
     Serif
    -0.08
     معه
    -0.08
     ácido
    -0.07
     معها
    -0.07
    .codegen
    -0.07
    613
    -0.07
     আল
    -0.07
     сте
    -0.07
     সঙ্গে
    -0.07
    POSITIVE LOGITS
    imini
    0.09
    設備
    0.09
    作为
    0.08
     ctr
    0.08
     düz
    0.08
    Kir
    0.08
    在線
    0.08
    場所
    0.08
     തീ
    0.08
    Membership
    0.07
    Activations Density 0.010%

    No Known Activations