© 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. 30439
    Prev
    Next
    INDEX
    Explanations

    bar

    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
    itados
    -0.08
    .TEXT
    -0.08
     DAR
    -0.08
     gleich
    -0.08
     Know
    -0.07
    ischt
    -0.07
     dictated
    -0.07
    GAIN
    -0.07
     Ras
    -0.07
     Geburt
    -0.07
    POSITIVE LOGITS
     emp
    0.08
    Ren
    0.08
    emp
    0.08
    Emp
    0.08
    secondary
    0.08
    0.07
    617
    0.07
     cevap
    0.07
    ದಿ
    0.07
    Ν
    0.07
    Activations Density 0.005%
    No Known Activations