© 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. 13268
    Prev
    Next
    INDEX
    Explanations

    troposphere

    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
     തീ
    -0.08
     dział
    -0.07
     efektif
    -0.07
    DISC
    -0.07
     capp
    -0.07
     Provincial
    -0.07
     Governance
    -0.07
    inded
    -0.07
     pristine
    -0.07
     സു�
    -0.07
    POSITIVE LOGITS
    /bin
    0.08
     OU
    0.08
     Flynn
    0.08
    Ou
    0.08
    vő
    0.07
     Ou
    0.07
     Koj
    0.07
     Ket
    0.07
    पास
    0.07
     ozone
    0.07
    Activations Density 0.002%

    No Known Activations