© 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. 44774
    Prev
    Next
    INDEX
    Explanations

    period

    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
     përd
    -0.08
     läh
    -0.08
    AGMA
    -0.08
     последнее
    -0.08
     bë
    -0.07
     최근
    -0.07
     juros
    -0.07
     Constituição
    -0.07
     típico
    -0.07
     legislação
    -0.07
    POSITIVE LOGITS
    120
    0.09
    180
    0.09
    60
    0.08
    100
    0.08
    127
    0.08
    080
    0.07
    six
    0.07
    121
    0.07
    260
    0.07
    860
    0.07
    Activations Density 0.006%

    No Known Activations