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. 23-RESID-POST-AA
    6. 98305
    Prev
    Next
    INDEX
    Explanations

    Cross-chain interoperability

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	op
    -0.08
     navigator
    -0.08
     beneficiaries
    -0.08
    op
    -0.08
     sahib
    -0.08
     역
    -0.07
    ophy
    -0.07
     governador
    -0.07
     château
    -0.07
    Immediately
    -0.07
    POSITIVE LOGITS
    xdd
    0.09
     Pol
    0.08
     Matrix
    0.08
     Rus
    0.08
     MATRIX
    0.07
    ATRIX
    0.07
    Matrix
    0.07
     hechos
    0.07
    .Security
    0.07
     RSS
    0.07
    Activations Density 0.001%

    No Known Activations