© 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. 23-RESID-POST-AA
    6. 5485
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     tq
    -0.09
    _trip
    -0.09
    /Y
    -0.08
    schutz
    -0.08
     taane
    -0.08
     wint
    -0.08
    верс
    -0.08
     toddlers
    -0.08
    ató
    -0.08
    alts
    -0.08
    POSITIVE LOGITS
     oriented
    0.08
    027
    0.08
    028
    0.08
    024
    0.08
    824
    0.08
    ೊ
    0.08
    023
    0.07
     intuition
    0.07
    026
    0.07
    ‍ക്ക
    0.07
    Activations Density 0.081%

    No Known Activations