© 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. 30147
    Prev
    Next
    INDEX
    Explanations

    blood pressure

    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
     mitigating
    -0.08
     verlassen
    -0.07
     Trait
    -0.07
     rune
    -0.07
    mission
    -0.07
    grave
    -0.07
    ļ
    -0.07
    -0.07
    porn
    -0.07
    Reasons
    -0.07
    POSITIVE LOGITS
     cuff
    0.09
     کابل
    0.09
    _ylim
    0.08
    [channel
    0.08
     cuffs
    0.08
     RPM
    0.08
    ifl
    0.08
     กรุงเทพ
    0.08
     Zusch
    0.08
     ವಾಹ
    0.08
    Activations Density 0.003%
    No Known Activations