© 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. 12999
    Prev
    Next
    INDEX
    Explanations

    not

    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
    /set
    -0.08
     ומת
    -0.07
     Julius
    -0.07
    .neg
    -0.07
    DEP
    -0.07
    DIS
    -0.07
     devoir
    -0.07
     parliamentary
    -0.07
    そこで
    -0.07
    Need
    -0.07
    POSITIVE LOGITS
    lah
    0.08
     capita
    0.07
     thou
    0.07
     litter
    0.07
    ਿ�
    0.07
     rushing
    0.07
    Clamp
    0.07
     hesitate
    0.07
     Macron
    0.07
     છો
    0.07
    Activations Density 0.015%

    No Known Activations