© 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. 11-RESID-POST-AA
    11. 30160
    Prev
    Next
    INDEX
    Explanations

    breach

    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
     flair
    -0.09
     Canarias
    -0.08
    èr
    -0.08
     brown
    -0.08
     گو
    -0.08
     Ghana
    -0.08
     Guatemala
    -0.07
    Ug
    -0.07
    wohl
    -0.07
     Glory
    -0.07
    POSITIVE LOGITS
     negligence
    0.08
    项
    0.08
     envers
    0.08
     fiduci
    0.07
     chores
    0.07
     partida
    0.07
    خي
    0.07
     duties
    0.07
    Field
    0.07
    項
    0.07
    Activations Density 0.005%

    No Known Activations