© 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. 23-RESID-POST-AA
    11. 6253
    Prev
    Next
    INDEX
    Explanations

    increasing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     declines
    -0.12
     descend
    -0.10
     Desc
    -0.10
    Desc
    -0.10
    desc
    -0.10
     downgrade
    -0.09
     descended
    -0.09
     Bonuses
    -0.09
     Exec
    -0.09
     Redemption
    -0.09
    POSITIVE LOGITS
     increasing
    0.25
    Increasing
    0.22
     Increasing
    0.20
     aumentando
    0.18
     zwięks
    0.17
     tăng
    0.16
     увеличить
    0.16
    增加
    0.16
     증가
    0.16
     увеличение
    0.16
    Activations Density 0.040%

    No Known Activations