© 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. 7-RESID-POST-AA
    6. 1068
    Prev
    Next
    INDEX
    Explanations

    jammed or stuck issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    囲
    -0.09
    bial
    -0.08
     Quel
    -0.08
     prefab
    -0.08
     bact
    -0.07
     Theft
    -0.07
     Mexico
    -0.07
     Alegre
    -0.07
     Rode
    -0.07
    *innen
    -0.07
    POSITIVE LOGITS
     stalled
    0.08
    dd
    0.08
     сөз
    0.08
     clogged
    0.08
     клав
    0.08
     tombol
    0.08
     один
    0.08
    .dd
    0.08
     сед
    0.07
     жүй
    0.07
    Activations Density 0.005%

    No Known Activations