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. 11-RESID-POST-AA
    6. 30533
    Prev
    Next
    INDEX
    Explanations

    natural consequences

    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
     Quick
    -0.09
    Quick
    -0.08
    Adapt
    -0.08
     Jewish
    -0.08
     nuclei
    -0.08
     Adapt
    -0.07
     instituciones
    -0.07
     QUICK
    -0.07
     Երբ
    -0.07
     փոխանց
    -0.07
    POSITIVE LOGITS
    ertura
    0.08
     확보
    0.08
    contest
    0.08
    "><?=$
    0.08
     strained
    0.08
     restoring
    0.07
     policing
    0.07
     inherent
    0.07
    raises
    0.07
    clared
    0.07
    Activations Density 0.001%

    No Known Activations