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. 53924
    Prev
    Next
    INDEX
    Explanations

    completion

    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
     खाली
    -0.08
     DWORD
    -0.08
     dangerously
    -0.07
    下来
    -0.07
     Caixa
    -0.07
     destinado
    -0.07
    ട്ട്
    -0.07
     campeonato
    -0.07
     dö
    -0.07
    湖
    -0.07
    POSITIVE LOGITS
    rechts
    0.10
    	elem
    0.08
     credits
    0.08
    Anywhere
    0.08
    -раз
    0.08
     степ
    0.08
    jis
    0.07
     inscriptions
    0.07
    jeva
    0.07
    reat
    0.07
    Activations Density 0.001%

    No Known Activations