© 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. 29679
    Prev
    Next
    INDEX
    Explanations

    t

    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
    organic
    -0.08
     agenda
    -0.08
     delic
    -0.08
    whatever
    -0.08
    agenda
    -0.07
     patio
    -0.07
     seminar
    -0.07
     अख
    -0.07
     politischen
    -0.07
     psych
    -0.07
    POSITIVE LOGITS
     denotes
    0.09
     Number
    0.08
     Seconds
    0.08
     Максим
    0.08
     :=
    0.08
     fij
    0.07
     khai
    0.07
     denote
    0.07
     summarizes
    0.07
     Stopwatch
    0.07
    Activations Density 0.043%

    No Known Activations