© 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. 64727
    Prev
    Next
    INDEX
    Explanations

    locate

    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
    276
    -0.08
    -0.07
     resolutions
    -0.07
     Resol
    -0.07
     resolves
    -0.07
    _RES
    -0.07
     resorts
    -0.07
    Transforms
    -0.07
    iði
    -0.07
    ieres
    -0.07
    POSITIVE LOGITS
     candid
    0.08
    ifdef
    0.08
     cộng
    0.08
     approfond
    0.08
    ్
    0.08
     použí
    0.08
     vos
    0.07
     danış
    0.07
     kanta
    0.07
    continuous
    0.07
    Activations Density 0.000%

    No Known Activations