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. 49078
    Prev
    Next
    INDEX
    Explanations

    Always/ever

    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
    Magnitude
    -0.08
     centrifugal
    -0.08
    icity
    -0.08
     kö
    -0.08
     Curse
    -0.08
    parcel
    -0.08
    inian
    -0.08
    rifice
    -0.07
     Fury
    -0.07
    送料
    -0.07
    POSITIVE LOGITS
     endeavors
    0.09
    积极
    0.09
     উদ্যোগ
    0.09
     initiatives
    0.08
     endeavor
    0.08
    準
    0.08
     misch
    0.08
     ventures
    0.08
     quests
    0.08
     తీ
    0.08
    Activations Density 0.009%

    No Known Activations