© 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. 23-RESID-POST-AA
    11. 97675
    Prev
    Next
    INDEX
    Explanations

    var

    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
    _minus
    -0.08
    itse
    -0.08
    Minus
    -0.08
     minus
    -0.08
    -minus
    -0.08
     shifting
    -0.07
     sine
    -0.07
     u
    -0.07
     skipping
    -0.07
     {_
    -0.07
    POSITIVE LOGITS
     kalla
    0.09
     broom
    0.08
     труб
    0.08
    ☴
    0.08
    ుల్
    0.08
    nothing
    0.08
     Income
    0.08
    ঞ
    0.08
     anba
    0.07
    ിഡ
    0.07
    Activations Density 0.001%

    No Known Activations