© 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. 12879
    Prev
    Next
    INDEX
    Explanations

    don't

    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
    突
    -0.08
     Rank
    -0.08
     opoz
    -0.07
    สูง
    -0.07
    ័យ
    -0.07
     naka
    -0.07
    ોદ
    -0.07
     നേ
    -0.07
    ճ
    -0.07
     ഉയ
    -0.07
    POSITIVE LOGITS
    CUS
    0.08
    CAB
    0.08
    Pid
    0.08
    FN
    0.08
    Suitable
    0.07
    Cu
    0.07
    PID
    0.07
     Reel
    0.07
    Gob
    0.07
    盆
    0.07
    Activations Density 0.000%

    No Known Activations