© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110609
    Prev
    Next
    INDEX
    Explanations

    writing and publishing

    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
     proficiency
    -0.09
    webe
    -0.08
     pono
    -0.08
     Eind
    -0.08
     efa
    -0.07
     poko
    -0.07
    eins
    -0.07
     Alleg
    -0.07
     anton
    -0.07
     unzip
    -0.07
    POSITIVE LOGITS
     crowdfunding
    0.13
    融资
    0.11
     financing
    0.11
     launching
    0.10
    创业
    0.10
    Launching
    0.10
    Rejected
    0.10
     funding
    0.10
    Funding
    0.09
     unsolicited
    0.09
    Activations Density 0.074%

    No Known Activations