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. 53794
    Prev
    Next
    INDEX
    Explanations

    day

    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
     Tw
    -0.08
     tw
    -0.08
    ાણી
    -0.08
     sparkle
    -0.08
     fib
    -0.08
     ટ્વ
    -0.08
     ट्व
    -0.08
    Tw
    -0.07
     ట్వ
    -0.07
     gepl
    -0.07
    POSITIVE LOGITS
     ampli
    0.09
    jad
    0.08
    -origin
    0.08
     thigh
    0.08
     resetting
    0.08
     thighs
    0.08
    -reset
    0.07
    handel
    0.07
     catast
    0.07
     metabolites
    0.07
    Activations Density 0.001%

    No Known Activations