© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 2554
    Prev
    Next
    INDEX
    Explanations

    pointers in list

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    лама
    -0.09
    crip
    -0.09
     kej
    -0.08
     ನಮ
    -0.08
     Zeppelin
    -0.08
     zeit
    -0.08
     whim
    -0.07
     lef
    -0.07
    лам
    -0.07
     المنام
    -0.07
    POSITIVE LOGITS
     dynamics
    0.07
    ி
    0.07
     siy
    0.07
    _SRC
    0.07
     brisk
    0.07
    borough
    0.07
     zako
    0.07
     tread
    0.07
    burn
    0.07
     rightly
    0.07
    Activations Density 0.008%

    No Known Activations