© 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. 1418
    Prev
    Next
    INDEX
    Explanations

    cré

    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
     Pont
    -0.07
     invoking
    -0.07
    കള
    -0.07
     стрел
    -0.07
     hel
    -0.07
     те
    -0.07
     jar
    -0.07
    違
    -0.07
    alupe
    -0.07
     ear
    -0.07
    POSITIVE LOGITS
    beek
    0.08
     Madeira
    0.08
     পত
    0.08
     복
    0.07
     kase
    0.07
     naka
    0.07
     Rad
    0.07
     Tan
    0.07
    עש
    0.07
     máximo
    0.07
    Activations Density 0.001%

    No Known Activations