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. 106193
    Prev
    Next
    INDEX
    Explanations

    lock

    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
     illumination
    -0.09
     illuminating
    -0.09
    Alignment
    -0.08
    -Dame
    -0.08
    _alignment
    -0.08
    辉
    -0.07
     넘어
    -0.07
    Gregorian
    -0.07
    iverse
    -0.07
    olocation
    -0.07
    POSITIVE LOGITS
    袋
    0.10
     Plast
    0.08
     pouch
    0.08
     seal
    0.08
     maxi
    0.08
     Plastik
    0.08
     plastics
    0.08
     plastik
    0.08
     freezer
    0.08
     klaus
    0.08
    Activations Density 0.010%

    No Known Activations