© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 45417
    Prev
    Next
    INDEX
    Explanations

    cue

    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
     Aman
    -0.08
    _sig
    -0.08
     fucking
    -0.07
    _Show
    -0.07
    _fp
    -0.07
     mellitus
    -0.07
     Anyways
    -0.07
    elle
    -0.07
     foreseeable
    -0.07
    ার্স
    -0.07
    POSITIVE LOGITS
    事項
    0.09
     scents
    0.08
     emotions
    0.08
     cues
    0.08
     제공
    0.08
     landmarks
    0.07
     masses
    0.07
     முட
    0.07
    kezt
    0.07
     emoções
    0.07
    Activations Density 0.012%

    No Known Activations