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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 48907
    Prev
    Next
    INDEX
    Explanations

    Rationality and legality

    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
     九
    -0.08
     सम्मेलन
    -0.08
     crowd
    -0.08
     lick
    -0.08
     kohe
    -0.08
     مشاريع
    -0.08
    ookie
    -0.08
     Selector
    -0.08
     Chocol
    -0.07
     ONG
    -0.07
    POSITIVE LOGITS
    Verd
    0.08
    Зам
    0.08
     Verd
    0.08
     techno
    0.08
     현대
    0.08
     Moderne
    0.08
     Protestant
    0.07
    -European
    0.07
    Univers
    0.07
     bureaucr
    0.07
    Activations Density 0.006%

    No Known Activations