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. 13005
    Prev
    Next
    INDEX
    Explanations

    guidelines

    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
    Incl
    -0.08
     acorde
    -0.08
    بارات
    -0.08
     развит
    -0.08
    -developed
    -0.08
    _BOOT
    -0.07
     بی
    -0.07
    -designed
    -0.07
    	typedef
    -0.07
    -real
    -0.07
    POSITIVE LOGITS
    0.08
    /stretchr
    0.07
    wrap
    0.07
    tap
    0.07
    kim
    0.07
    sharing
    0.07
    ki
    0.07
    listing
    0.07
    :Is
    0.07
    kun
    0.07
    Activations Density 0.149%

    No Known Activations