Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 156
    Prev
    Next
    INDEX
    Explanations

    water

    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
     motivational
    -0.09
    ум
    -0.09
     Today's
    -0.08
     qualifying
    -0.08
    ечес
    -0.08
    ಾನು
    -0.08
     motivations
    -0.08
     memorable
    -0.08
     मानसिक
    -0.08
     motives
    -0.08
    POSITIVE LOGITS
     clogged
    0.10
     redistributed
    0.10
     redistribution
    0.10
     reagieren
    0.10
     reager
    0.10
     suction
    0.09
     evacuated
    0.09
     fiquei
    0.09
     erupted
    0.09
     reageren
    0.09
    Activations Density 0.006%

    No Known Activations