© 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. 13207
    Prev
    Next
    INDEX
    Explanations

    ax

    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
     Aspir
    -0.08
    cup
    -0.08
     Delphi
    -0.08
    oil
    -0.07
     Nicholson
    -0.07
    =:
    -0.07
    _union
    -0.07
     Cath
    -0.07
     Nish
    -0.07
     uitbre
    -0.07
    POSITIVE LOGITS
    Harness
    0.08
     premier
    0.07
     literally
    0.07
     Wichita
    0.07
     harness
    0.07
    �
    0.07
     Saddle
    0.07
    Msg
    0.07
     viv
    0.07
     gerecht
    0.07
    Activations Density 0.001%

    No Known Activations