© 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. 3-RESID-POST-AA
    6. 2964
    Prev
    Next
    INDEX
    Explanations

    –

    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
     dont
    -0.08
     Nov
    -0.07
    wax
    -0.07
     vt
    -0.07
     Ash
    -0.07
     Diss
    -0.07
    Reply
    -0.07
     Nep
    -0.07
     심
    -0.07
    Wr
    -0.07
    POSITIVE LOGITS
    Horn
    0.08
     cố
    0.07
    tal
    0.07
    dz
    0.07
     bore
    0.07
     Karen
    0.07
     thi
    0.07
    ADF
    0.07
    bom
    0.07
    Able
    0.07
    Activations Density 0.038%

    No Known Activations