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. 11851
    Prev
    Next
    INDEX
    Explanations

    code, software configurations

    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
    ங்கள
    -0.08
     narrowing
    -0.08
    作文
    -0.08
     narrowed
    -0.08
     flop
    -0.07
     допуст
    -0.07
    ன்ன
    -0.07
     entertain
    -0.07
     соч
    -0.07
    	fmt
    -0.07
    POSITIVE LOGITS
    Daemon
    0.13
     daemon
    0.13
    daemon
    0.12
    /background
    0.09
    Background
    0.09
    -background
    0.09
    continuous
    0.09
    Kwa
    0.09
     Autón
    0.09
     Background
    0.09
    Activations Density 0.009%

    No Known Activations