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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 68763
    Prev
    Next
    INDEX
    Explanations

    Comparisons and examples

    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
     분
    -0.08
     어느
    -0.08
     wela
    -0.08
    uenta
    -0.08
    ouble
    -0.08
     ウ
    -0.07
     preferably
    -0.07
     kör
    -0.07
     przeciw
    -0.07
    jski
    -0.07
    POSITIVE LOGITS
     clich
    0.12
     clichés
    0.10
     cliché
    0.08
     uncommon
    0.08
     unless
    0.08
     সফ
    0.07
     narration
    0.07
     obvious
    0.07
     usual
    0.07
     generic
    0.07
    Activations Density 0.016%

    No Known Activations