© 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. 95813
    Prev
    Next
    INDEX
    Explanations

    keep

    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
    ಿಗ್ಗ
    -0.08
    /ec
    -0.08
     प्रक
    -0.07
     পরিচাল
    -0.07
    VN
    -0.07
     mangel
    -0.07
    atility
    -0.07
     mortal
    -0.07
     erheb
    -0.07
    _pad
    -0.07
    POSITIVE LOGITS
     behalten
    0.09
     intact
    0.09
     preserving
    0.09
    択
    0.08
    拼
    0.08
     retention
    0.08
     retaining
    0.08
     preservar
    0.08
    的是
    0.08
     Punch
    0.08
    Activations Density 0.016%

    No Known Activations