© 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. 11-RESID-POST-AA
    11. 129097
    Prev
    Next
    INDEX
    Explanations

    Math inequalities

    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
    black
    -0.08
     Rubber
    -0.08
    Ü
    -0.07
     spider
    -0.07
    alloc
    -0.07
     Kw
    -0.07
     rubber
    -0.07
    -SP
    -0.07
    ocup
    -0.07
    ement
    -0.07
    POSITIVE LOGITS
     অবশ্য
    0.09
    უსტ
    0.08
     ascii
    0.08
    հանուր
    0.08
    abcdefghijkl
    0.07
     resten
    0.07
    ისპ
    0.07
     ==>
    0.07
     използ
    0.07
    ასტ
    0.07
    Activations Density 0.021%

    No Known Activations