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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2650
    Prev
    Next
    INDEX
    Explanations

    message

    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
     Για
    -0.07
    .phot
    -0.07
    bart
    -0.07
    aneous
    -0.07
    rosis
    -0.07
    riangle
    -0.07
     Rogers
    -0.07
    Falls
    -0.07
    影视
    -0.07
    riend
    -0.07
    POSITIVE LOGITS
     cylind
    0.08
     chiếc
    0.08
     ಹೆ
    0.08
    0.08
     ಪ
    0.08
     waiver
    0.08
     словам
    0.08
    Sis
    0.08
     cruiser
    0.08
    lys
    0.07
    Activations Density 0.010%
    No Known Activations