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. 19080
    Prev
    Next
    INDEX
    Explanations

    =

    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
    Lastly
    -0.08
     condiment
    -0.08
     largely
    -0.07
    uret
    -0.07
    …
    -0.07
     continually
    -0.07
    Fallback
    -0.07
     counselor
    -0.07
     alarms
    -0.07
    ímp
    -0.07
    POSITIVE LOGITS
     aantal
    0.09
     denote
    0.08
     hran
    0.08
    ",".
    0.08
     территория
    0.08
     reprez
    0.08
     Anzahl
    0.08
    	ac
    0.08
    ethi
    0.08
     تعداد
    0.08
    Activations Density 0.016%

    No Known Activations