© 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. 49170
    Prev
    Next
    INDEX
    Explanations

    recipes and knitting

    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
     swin
    -0.08
     de
    -0.08
     owning
    -0.07
    uret
    -0.07
    agal
    -0.07
    #ac
    -0.07
    apen
    -0.07
    -devel
    -0.07
     wifi
    -0.07
    anay
    -0.07
    POSITIVE LOGITS
    XHR
    0.09
    jaars
    0.09
    .Payload
    0.08
    moment
    0.08
    Momentum
    0.08
     დატ
    0.08
     kachasị
    0.08
     iṣelọpọ
    0.08
    .Integer
    0.08
    _chunks
    0.08
    Activations Density 0.000%

    No Known Activations