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. 43838
    Prev
    Next
    INDEX
    Explanations

    a, an articles

    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
     항상
    -0.09
     हमेशा
    -0.08
     bmp
    -0.08
    ചര
    -0.07
    Todo
    -0.07
     tempered
    -0.07
     മാർ
    -0.07
     benötigen
    -0.07
     circulate
    -0.07
    	scanf
    -0.07
    POSITIVE LOGITS
     dim
    0.09
     nutshell
    0.08
    ೕ
    0.08
    IMAL
    0.08
     university
    0.08
     continuation
    0.07
    主
    0.07
    udza
    0.07
     NZ
    0.07
     Butterfly
    0.07
    Activations Density 0.105%

    No Known Activations