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. 19091
    Prev
    Next
    INDEX
    Explanations

    a

    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
     আলোচনা
    -0.08
    herent
    -0.08
    uty
    -0.08
     edildi
    -0.08
     আহ
    -0.07
    োৰ
    -0.07
     memil
    -0.07
     చేసింది
    -0.07
     ibikorwa
    -0.07
    abcdefghijklmnopqrstuvwxyz
    -0.07
    POSITIVE LOGITS
     목표
    0.15
     someday
    0.14
     원하는
    0.13
     goals
    0.13
     goal
    0.13
     लक्ष्य
    0.12
     gewenste
    0.12
     ലക്ഷ
    0.12
     desired
    0.12
    目标
    0.12
    Activations Density 0.024%

    No Known Activations