© 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. 3-RESID-POST-AA
    11. 13349
    Prev
    Next
    INDEX
    Explanations

    office

    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
     donate
    -0.09
    jes
    -0.08
     uter
    -0.08
     tightly
    -0.08
     topped
    -0.08
     dashed
    -0.08
     collaborate
    -0.08
     UC
    -0.08
     vaginal
    -0.08
    (Bytes
    -0.08
    POSITIVE LOGITS
     Threads
    0.09
    Threads
    0.08
    Seeking
    0.08
    �
    0.07
    otom
    0.07
    .song
    0.07
    鳥
    0.07
    hq
    0.07
    _threads
    0.07
    INDEX
    0.07
    Activations Density 0.015%

    No Known Activations