© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 16621
    Prev
    Next
    INDEX
    Explanations

    2

    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
     that
    -0.10
     the
    -0.08
     qui
    -0.08
     compare
    -0.08
     this
    -0.08
     SAC
    -0.07
     constraints
    -0.07
     much
    -0.07
     division
    -0.07
     too
    -0.07
    POSITIVE LOGITS
     և
    0.10
    (reverse
    0.10
     gegense
    0.10
    _bid
    0.10
     variantes
    0.10
    aliases
    0.09
    ագետ
    0.09
     variants
    0.09
    -direction
    0.09
     iba't
    0.09
    Activations Density 0.022%

    No Known Activations