© 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. 12947
    Prev
    Next
    INDEX
    Explanations

    bands

    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
     presso
    -0.08
     zg
    -0.08
     substant
    -0.07
     lurking
    -0.07
     handled
    -0.07
    -comp
    -0.07
     Francis
    -0.07
    سر
    -0.07
     Tet
    -0.07
     ze
    -0.07
    POSITIVE LOGITS
     Finish
    0.08
     faixa
    0.07
    (strings
    0.07
     Canary
    0.07
    icar
    0.07
     thickness
    0.07
     Finished
    0.07
    ്ധ
    0.07
     reina
    0.07
     finished
    0.07
    Activations Density 0.014%

    No Known Activations